Furkan Gözükara

Posted on Nov 4

SwarmUI Full Tutorial: 1-Click Install, 4 MP Images, Full HD Video with Sound, Lip Sync & Edits

Full tutorial link > https://www.youtube.com/watch?v=0HmIeeI1iBo

SwarmUI, set up with our one-click installers, our model downloader (35+ bundles, 517+ models) and 86+ ready presets, turns your own PC into a complete AI studio: 4-megapixel images, one-prompt edits, full HD MiniMax H3 videos with speech, sound effects and music, lip sync and Genjutsu person swaps. This tutorial installs everything from zero on Windows and teaches every feature step by step; the same installers run on RunPod, SimplePod, Massed Compute and Linux.

Links:

Download the SwarmUI installer, model downloader and presets (our SwarmUI post): [ https://www.patreon.com/posts/swarmui-auto-and-114517862 ]

ComfyUI backend installer (our ComfyUI post): [ https://www.patreon.com/posts/105023709 ]

One-time Windows requirements installer tutorial: [ https://youtu.be/ptuLL0C72Ms ]

SwarmUI + ComfyUI on cloud GPUs (RunPod, Massed Compute): [ https://youtu.be/bBxgtVD3ek4 ]

SimplePod tutorial: [ https://youtu.be/yOj9PYq3XYM ]

SECourses Discord: [ https://discord.com/invite/software-engineering-courses-secourses-772774097734074388 ]

You will learn the full route on a fresh Windows PC: download and extract both packages, install our ComfyUI backend and SwarmUI, connect them, import our presets, download models in one-click bundles and update everything, then every image, edit, video, lip-sync, audio and tool feature listed in the chapters below.

Main topics include MiniMax H3 and FastH3, Krea 2 Turbo, Qwen Image 2.1, FLUX 3 Klein, FLUX Fill and Kontext, Ideogram 4, Z Image, SDXL, LTX 2.3, SVI 2 Pro, Genjutsu, Long Lip Sync, RefMods and our LLM prompt kits. Every result was made on the fresh install with an RTX 5090.

Use the chapters to jump to any install step, feature, setting or comparison.

Chapters:

00:00:00 One prompt: H3 video with speech, effects and music

00:01:04 What our installers, downloader and presets add

00:02:23 Quick first image at 4 MP with Krea 2 Turbo

00:03:36 Download both zips from our posts

00:06:16 Create the folders and extract both packages

00:07:45 Install our ComfyUI backend: Torch 2.13, CUDA 13

00:09:10 Install SwarmUI with one double-click, first-run setup

00:11:32 Connect the ComfyUI backend and its arguments

00:13:22 Import our 86 presets with one bat file

00:14:10 The routine: reset, then Direct Apply a preset

00:15:09 Model downloader: the Krea 2 bundle in one click

00:18:24 More bundles, single models, URL downloads

00:20:38 First 4 MP image, bundle cards and model report

00:23:05 Update in six steps, verified models kept

00:27:58 What one preset click sets, our 11 extensions

00:29:50 Tour of the Generate page

00:32:43 Find the right preset for each job

00:34:35 Text in images: Ideogram 4 vs Qwen Image 2.1

00:36:59 Size, aspect ratio and our Megapixels option

00:38:09 Images, seeds and Variation Seed

00:39:56 Steps 4, 8, 16 compared; CFG, sampler, Sigma Shift

00:41:47 SDXL: negative prompt and CFG 3, 7, 12 compared

00:44:08 Z Image seed variety trick, Reuse Parameters

00:46:10 Prompt weights, alternate and from-to syntax

00:48:34 Regional prompt: a white wolf in one area

00:49:18 Random picks, wildcards and variables

00:52:21 Auto segment faces, more tags, LLM prompt kits

00:54:36 LoRAs: Skin Fix at weight 0.6 vs 1.0

00:57:06 FLUX Kontext edit and fixing model metadata

00:59:41 Refine and upscale a draft to 4 MP

01:02:32 Init Image creativity 0.3, 0.55 and 0.8

01:04:41 Inpaint a dragon: Image Editor and SAM 2 masks

01:07:35 Remove a watermark, every other pixel kept

01:10:12 Outpainting in small steps with FLUX Fill

01:13:53 Qwen Image 2.1: gold armor from one prompt

01:16:23 Combine images; FLUX 3 Klein vs Qwen edit

01:18:46 Layout boxes place every object exactly

01:21:46 ControlNet Canny and Redux style transfer

01:26:12 Attach media, trim clips, prompt batches

01:29:03 H3 references, @ tokens and the token meter

01:30:48 Write an H3 prompt with our kit and Gemini

01:31:52 Text to video with sound: MiniMax H3 at 1080p

01:33:35 8-step turbo LoRA vs 20 steps, RIFE smoothing

01:36:14 Image to video: the portrait moves and speaks

01:37:42 First and last frame: black armor to gold

01:39:02 Video to video with LTX 2.3: anime style

01:40:15 Genjutsu: swap the person, keep every move

01:43:12 Longer videos: continue a clip, SVI 2 Pro

01:46:21 Long Lip Sync: a portrait speaks in full HD

01:49:39 References to video: face, dragon and voice

01:51:15 Save a character and voice as a RefMod

01:53:44 Sound only with H3, Foley for a silent clip

01:57:19 Grid Generator: samplers by steps

01:59:51 Compare results, History and the video editor

02:02:18 The ComfyUI workflow behind a preset

02:04:16 Speed overrides and a second GPU backend

02:06:04 Server, user settings, Utilities and the API

02:09:20 Recap and where to download everything

4 November 2026 Update V189

Edit real videos with MiniMax H3 in SwarmUI. Five new presets: replace the background of any video from one image, relight a whole clip, put a new face on someone, replace a person or object while every other pixel stays as filmed, and make long Pika H3 Flex videos that follow a story, scene by scene.

Amazing SwarmUI Presets moves to V88 with 99 presets: 5 new since V86, every earlier preset unchanged.

Real footage and real runs of the shipped presets:

Every result in this post comes from a real run of the shipped presets in SwarmUI.

All 99 presets in the Presets tab, the new ones marked NEW:

The new presets up close, each with its own animal thumbnail:

Windows_Preset_Delete_Import.bat brings all of them into your SwarmUI; the steps are in How to update at the end.

To run them, download the MiniMax-H3 Core Bundle. It includes the FaceSwap LoRA; if you already have the bundle, only the missing files download:

All the new presets use this one bundle.

Our live token counter is above the prompt: it counts your text, references, audio and video as you work and shows them against the MiniMax H3 limit, in green, amber and red, so you know what a run needs before you click Generate.

NEW PRESET — BACKGROUND REPLACE: YOUR VIDEO, A NEW BACKGROUND, NOTHING ELSE

"MiniMax H3 Background Replace - Pika H3 Flex 6 Steps - 261104"

Fully automatic: attach your video and a background image, and click Generate. The person is found by itself and stays exactly as filmed: every pixel of the face, hair, clothes and hands, the lip movements, the timing and the sound. Everything around them becomes the place in your image and moves with your camera.

Where to find it: Presets tab → filter 261104 → apply the preset, attach both files beside the prompt and click Generate. There is nothing to write or set. Long clips work too: the video is made in overlapping windows, so a long clip needs no more GPU memory, only more time. The result is about 1 megapixel. People of similar size all stay, and distant passers-by go.

NEW PRESET — VIDEO RELIGHT

"MiniMax H3 Video Relight - Pika H3 Flex 6 Steps - 261104"

Relight a whole video. Attach your clip and click Generate: the prompt already holds a complete neon noir lighting plan. The people, the motion, the camera and the set stay.

Where to find it: Presets tab → filter 261104. Change the colours or directions in the Lighting plan lines of the prompt. H3 follows the plan through the prompt, so it is not pixel-exact light control; try two or three seeds.

NEW PRESET — FACE SWAP

"MiniMax H3 Face Swap - Ref2VA 8 Steps - 261104"

Put a new face on the person in your video. Attach your clip and a clear close-up of the new face, leave the prompt empty and click Generate. Clothes, setting and camera stay as in your clip.

H3 makes the whole clip anew, so the timing of the motion can drift a little. For your clip's exact timing and sound, use the Masked Edit preset below with Genjutsu Target set to head.

NEW PRESET — GENJUTSU MASKED EDIT: CHANGE ONE THING, KEEP EVERYTHING ELSE

"MiniMax H3 Genjutsu - Masked Edit - Pika H3 Flex 6 Steps - 261104"

Replace a person or an object and keep the rest of your clip exactly as filmed. Attach your clip and the new character and click Generate: the person is found and the prompt is written for you. The street, the traffic, the signs and the camera move stay untouched.

Where to find it: Presets tab → filter 261104. To replace something else, name it in Genjutsu Target: a car, a dog, a man in a blue suit.

NEW PRESET — PIKA H3 FLEX LONG VIDEO THAT TELLS A STORY

"Pika H3 Flex - Long Text to Video 20 Seconds - 261104"

A long video that develops instead of repeating. Write your description, then a line with ---, then one scene, another ---, the next scene. Each part of the video follows its own scene.

Five scenes in one prompt, one continuous 20-second flight:

Where to find it: Presets tab → filter 261104. About 4 seconds per scene works well; set Text2Video Frames for other lengths (481 = 20 s, 719 = 30 s). Without --- every window reads the same prompt, so motion can repeat. Scenes work in text runs, not with reference media.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v189.zip from this post and extract it over your downloader folder.
Close SwarmUI and run Windows_Install_or_Update_SwarmUI.bat.
Update the ComfyUI backend. With our ComfyUI installation, close SwarmUI again (step 2 starts it) and run Windows_Install_Or_Update_ComfyUI.bat from our ComfyUI V149. With SwarmUI's own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start.
Restart SwarmUI, then run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v88.json. It backs up your current presets first, then replaces them all, your own presets too.
Run Windows_Start_Download_Models_App.bat and download the MiniMax-H3 Core Bundle.

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709

30 October 2026 Update V187

Pika H3 Flex: cinematic video with synchronized sound in 6 steps. Three new presets bring Pika Labs' new Pika H3 Flex to SwarmUI: text to video, beginning and ending frame to video and references to video, each with dialogue, sound effects and music made together with the picture.

Amazing SwarmUI Presets moves to V86 with 94 presets: 3 new, every earlier preset unchanged.

Our three examples: a ship in a bottle that sails out onto a stormy ocean, a blacksmith whose golden eagle lands on his anvil, and an airship captain made from just two images:

Every result in this post is a real run of the shipped presets in SwarmUI on our RTX 5090.

All 94 presets of Amazing SwarmUI Presets V86 in SwarmUI's Presets tab, the new ones marked NEW:

The 3 new presets up close, each with its own animal thumbnail:

Windows_Preset_Delete_Import.bat brings all of them into your SwarmUI; the steps are in How to update at the end.

NEW PRESETS — PIKA H3 FLEX: VIDEO WITH SOUND IN 6 STEPS

"Pika H3 Flex - Text to Video 6 Steps - 261030"

"Pika H3 Flex - Beginning and Ending Frame to Video 6 Steps - 261030"

"Pika H3 Flex - References to Video 6 Steps - 261030"

Pika's tuned MiniMax H3, in 6 steps. A 5-second 1344 × 768 clip with stereo sound takes about a minute on an RTX 5090. Init Audio, face inpainting and your own MiniMax H3 LoRAs stay available, as in every MiniMax H3 preset.

To run them, download the MiniMax-H3 Core Bundle. It now includes the two Pika H3 Flex LoRAs; if you already have the bundle, only those 3.6 GB download:

Beginning and Ending Frame: give it two images and it makes the shot between them. Our ship in a bottle becomes the real ship on the open sea in one continuous camera move:

Where to find it: Presets tab → filter Pika → Direct Apply Pika H3 Flex - Beginning and Ending Frame to Video 6 Steps - 261030. Put the beginning frame in Init Image, tick Display Advanced Options and put the ending frame in Image To Video → Video End Image, then click Generate:

Start the prompt with Pika's timing line; the preset description has it ready to copy. Leave Video End Image empty for first frame to video.

Text to Video: one prompt gives the whole scene, with the blacksmith's line, the hammer, the hiss of steam and the eagle's wingbeats in the soundtrack:

References to Video: attach a character image and a place image beside the prompt; our captain walks his sky harbour with his beard, goggles, green scarf and compass kept:

The MiniMax H3 prompt guide now covers Pika H3 Flex, so ChatGPT, Claude or Gemini can write your prompts.

ALSO IN V187

The MiniMax-H3 Low VRAM Bundle includes the two Pika H3 Flex LoRAs too.
SwarmUI's scheduler list gains pika_h3_flex, Pika's official 6-step schedule, after the update below.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v187.zip from this post and extract it over your downloader folder.
Close SwarmUI and run Windows_Install_or_Update_SwarmUI.bat.
Update the ComfyUI backend. With our ComfyUI installation, close SwarmUI again (step 2 starts it) and run Windows_Install_Or_Update_ComfyUI.bat from our ComfyUI V147. With SwarmUI's own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start.
Restart SwarmUI, then run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v86.json. It backs up your current presets first, then replaces them all, your own presets too.
Run Windows_Start_Download_Models_App.bat and download the MiniMax-H3 Core Bundle.

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709

28 October 2026 Update V186

Anima character transfer, MOSS-Image layout control, stronger MiniMax H3 Genjutsu and faster FastH3 decoding. Put one character into any scene with Anima, place and pose people with simple color and depth maps in MOSS-Image, swap characters in your clips more convincingly with the new Genjutsu task LoRAs, and decode FastH3 Omni videos faster with LightVAE.

Amazing SwarmUI Presets moves to V85 with 91 presets: 5 new, 2 updated, and 24 others now switch the new options off when you apply them.

With the adapter's example maps, both new MOSS-Image presets put the two men where the mannequins stand, in their poses; without maps, the same prompt and seed picks its own layout:

Every result in this post is a real run of the shipped presets in SwarmUI on our RTX 5090.

All 91 presets of Amazing SwarmUI Presets V85 in SwarmUI's Presets tab, the new ones marked NEW and the updated ones UPDATED:

The 5 new and 2 updated presets up close:

Windows_Preset_Delete_Import.bat brings all of them into your SwarmUI; the steps are in How to update at the end.

NEW PRESETS — ANIMA: TAKE YOUR CHARACTER INTO A NEW SCENE

"Anima - Advanced Text To Image - 261028"

"Anima - Reference Character And Style - 261028"

One image of your character, any new scene. The Anima reference adapter carries the face, hair and outfit, and part of the drawing style, from your image, while your prompt picks the pose, place and light. Every final image is a clean 2048 × 2048.

To run them, download the Anima Core Bundle (3.84 GB) from the model downloader:

Our example: one character made with text to image, then four new scenes from that single image with one click on Generate prompt batch:

Where to find it: Presets tab → filter Anima → Direct Apply Anima - Reference Character And Style - 261028. Upload your character in Anima Reference Image, add your scene prompts and click Generate prompt batch:

The new Anima_Enchance_Prompt_Feed_For_LLMs.txt lets ChatGPT, Claude or Gemini write your prompts or a whole scene series.

NEW PRESETS — MOSS IMAGE COLOR + DEPTH CONTROL: PLACE YOUR PEOPLE WITH A MAP

"MOSS Image - Color + Depth Control - 261027"

"MOSS Image - Turbo 8 Steps Color + Depth Control - 261027"

Draw the layout, MOSS-Image follows it. A color map marks where each person or object goes, a depth map shows what is near and far, and your prompt says who they are. Turbo makes a 1024 × 1024 image in about 4 seconds.

To run them, download the MOSS-Image Core Bundle. It now includes the color + depth adapter; if you already have the bundle, only that 0.29 GB file downloads:

Where to find it: Quick Tools → Reset Params to Default, then Presets tab → filter Color + Depth → Apply. Add your maps with the Upload buttons of MOSS Image Color Map and MOSS Image Depth Map, describe each person and press Generate:

Part 8 of the MOSS-Image prompt guide writes the prompt for your maps.

NEW PRESET — FASTH3 OMNI WITH THE LIGHTVAE VIDEO DECODER

"FastH3 Omni - LightVAE References to Video 8 Steps - 261027"

The same FastH3 Omni video, decoded faster. LightVAE by LightX2V decoded and saved our 5-second video in about 4 seconds instead of about 6.5, with frames that look the same.

To run it, download the FastH3 Omni Core Bundle. It now includes the LightVAE decoder and the three Genjutsu files:

Where to find it: Quick Tools → Reset Params to Default, then Presets tab → filter LightVAE → Apply. The new MiniMax H3 Video Decoder parameter in Core Parameters picks the decoder for any MiniMax H3 or FastH3 Omni model:

Set it to None for the original decoder; every other H3 preset does that for you.

UPDATED PRESETS — MINIMAX H3 GENJUTSU: CHARACTER SWAP AND MOTION TRANSFER LORAS

"MiniMax H3 Genjutsu - FastH3 Omni 8 Steps - 261024"

"MiniMax H3 Genjutsu - Ref2VA 20 Steps - 261024"

Swap the person in any clip for your character, now with task LoRAs trained for exactly this job. Character Swap v1.1 and Motion Transfer v1.0 by Alisson Anjos bring your character's look over much more closely, and clips with mono sound now work.

The FastH3 Omni 8 Steps preset uses the FastH3 Omni Core Bundle above. The Ref2VA 20 Steps preset uses the MiniMax-H3 Core Bundle, which now includes the three Genjutsu files:

Same warrior, same shadowboxing clip, same seed: the original method and the new task LoRA default:

The task LoRA brings his big scale shoulder guards and heavy build over. original Genjutsu is still one click away in Genjutsu Method.

Where to find it: Quick Tools → Reset Params to Default, then Presets tab → filter H3 Genjutsu → Apply. Attach the clip and your character with Add References and press Generate:

Low VRAM mode is on by default with the same output.

ALSO IN V186

The MiniMax-H3 Low VRAM Bundle and the Complete Image Generation and Editing Bundle include the new models too.
The Krea 2 and FLUX 3 Klein bundles no longer download their shared text encoder again on every run.
MiniMax H3 Long Lip Sync - References no longer adds a second pass after an image-to-video preset: about 5.5 minutes instead of 11.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v186.zip from this post and extract it over your downloader folder.
Close SwarmUI and run Windows_Install_or_Update_SwarmUI.bat.
Update the ComfyUI backend. With our ComfyUI installation, close SwarmUI again (step 2 starts it) and run Windows_Install_Or_Update_ComfyUI.bat from our ComfyUI V146. With SwarmUI's own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start.
Restart SwarmUI, then run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v85.json. It backs up your current presets first, then replaces them all, your own presets too.
Run Windows_Start_Download_Models_App.bat and download the core bundles shown above.

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709

24 October 2026 Update V185

This is a MiniMax H3 Genjutsu update. V185 adds two presets that replace the person in any video with your own character: attach your clip and one image of the new character, press Generate, and the result keeps the clip's motion, timing, camera, length, aspect ratio and original sound. Our MiniMaxH3References extension gets the new MiniMax H3 Genjutsu group, and the model downloader adds SAM 3.1 and Qwen3-VL 8B to the MiniMax H3 and FastH3 Omni bundles.

Amazing SwarmUI Presets moves to V84 with 86 presets: the two new presets, and the other 84 presets unchanged.

Our test in SwarmUI: this armoured warrior image and a 9.8-second phone clip of a man shadowboxing in a gym. Both presets put the warrior into the clip, punch for punch and step for step, in the clip's portrait format and with its own sound:

Exact V184 → V185 zip audit:

Presets: Amazing_SwarmUI_Presets_v83.json was replaced by Amazing_SwarmUI_Presets_v84.json. Its 84 presets are unchanged in every setting, description and thumbnail; 2 presets are new.
6 changed files: the model catalog and its size data (SAM 3.1 and Qwen3-VL 8B in the MiniMax-H3 Core, MiniMax-H3 Low VRAM and FastH3 Omni Core bundles), update_swarmui.py (a premium extension that could not be replaced during an update is installed again by the next update), the downloader app (shows v185), the regenerated Which_Bundles_Downloads_Which_Preset_Models.html and the MiniMax H3 prompt guide (new Genjutsu section).

NEW PRESETS — MINIMAX H3 GENJUTSU: PUT YOUR CHARACTER INTO ANY VIDEO

"MiniMax H3 Genjutsu - FastH3 Omni 8 Steps - 261024" "MiniMax H3 Genjutsu - Ref2VA 20 Steps - 261024"

How it works: SAM 3.1 finds the person in every frame of your clip, and only that person is colour-inverted. MiniMax H3 then copies the clip's motion, timing, camera and lip movements, but not the performer's face, hair or clothes. A local Qwen3-VL 8B (Auto Describe) looks at your character image and six frames of the clip and writes the prompt for you: the new outfit, the action, the setting, the lighting and the framing. The clip's soundtrack is locked into MiniMax H3's audio stream for lip sync, and the saved video carries the original sound.

Where to find it: Quick Tools → Reset Params to Default, then the Presets tab → type Genjutsu in the filter → the preset card's menu → Direct Apply. Attach the clip and the character image with Add References (or Add A Reference With Trim to pick the part of the clip) and press Generate. Here is the FastH3 Omni preset after a real run of our example:

MiniMax H3 Genjutsu (on): turns the first reference video into the SAM 3.1 motion guide.
Genjutsu Background: video (character replacement) keeps the clip's location, lighting and framing; image (motion transfer) keeps your character image's background and takes only the motion.
Genjutsu Target: who to replace, in plain words: person, or man in red:1 to pick one of several people.
Genjutsu Auto Describe (on): the local Qwen3-VL 8B writes the outfit, action, setting, lighting and framing into the prompt. Leave the prompt empty, type short notes, or paste a complete MiniMax H3 prompt from ChatGPT, Claude or Gemini; a complete prompt is used as written.
Genjutsu Spoken Words (optional): the words spoken in the clip, for word-by-word lip sync.
Genjutsu Lock Clip Audio (on) and Genjutsu Match Clip Aspect (on): the clip's sound drives the lip movements, and the output takes the clip's aspect ratio at your Width x Height area.
Genjutsu Motion Guide Megapixels (0.15): the guide size; advanced options set the detection threshold and the mask grow.
The output follows the clip: our 9.8-second 1080x1920 clip gave 226 frames (9.4 seconds) at 768x1344, and the token meter beside the prompt shows that length and size before you press Generate.
Speed: FastH3 Omni 8 steps made the 9.4-second example in 4.5 minutes and Ref2VA 20 steps in 9.9 minutes in SwarmUI, first runs with model loading on an RTX 5090.

MODEL DOWNLOADER — SAM 3.1 AND QWEN3-VL 8B IN THE MINIMAX H3 BUNDLES

The MiniMax-H3 Core Bundle, the MiniMax-H3 Low VRAM Bundle and the FastH3 Omni Core Bundle now download everything the Genjutsu presets use:

SAM 3.1 Multiplex FP16 (1.63 GB, saved to Models/Stable-Diffusion): finds the person to replace in every frame.
Qwen3-VL 8B INT8 ConvRot (8.71 GB, saved to Models/text_encoders): writes the Genjutsu prompt. It is the same file as the Qwen Image 2.1 encoder, so if you already have it, the downloader checks it and keeps it.
New totals: MiniMax-H3 Core Bundle 79.91 GB (19 files), MiniMax-H3 Low VRAM Bundle 64.21 GB (19 files), FastH3 Omni Core Bundle 60.12 GB (11 files), sizes as the downloader shows them.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v185.zip from this post and extract it over your existing downloader folder.
Close SwarmUI and run Windows_Install_or_Update_SwarmUI.bat. It installs MiniMaxH3References 1.22.1 and our FoleyExtension with the Genjutsu nodes.
Keep the ComfyUI backend up to date. If SwarmUI uses our ComfyUI installation, close SwarmUI again (step 2 starts it, and a running backend blocks the update) and update that ComfyUI with our ComfyUI installer V145 (Windows_Install_Or_Update_ComfyUI.bat), which also brings the same Genjutsu presets to ComfyUI. If SwarmUI uses its own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start.
Restart SwarmUI and its ComfyUI backend so the new extension and nodes register.
With SwarmUI running, run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v84.json. It backs up your current presets, thumbnails included, to utilities\presets_backups, deletes them all (your own presets too) and imports the new pack.
Run Windows_Start_Download_Models_App.bat and download the MiniMax-H3 Core Bundle or the FastH3 Omni Core Bundle (the files you already have are checked and kept).

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709

23 October 2026 Update V184

This is a Fibo 2.0, MOSS Image Edit and FastH3 Omni update. V184 adds four presets for Bria's Fibo 2.0, which generates and edits images from long JSON captions, two MOSS Image Edit presets that edit your photos with a short instruction, and four FastH3 Omni presets that turn your images, videos and sounds into video with synchronized audio, stills or audio in 8 steps. The model downloader gets the FastH3 Omni and Fibo 2.0 Core Bundles and a redesigned, much faster interface, keeps the model files whose header SwarmUI rewrote instead of downloading them again, and fixes the Qwen Image 2.1 text encoder that SwarmUI downloaded a second time.

Amazing SwarmUI Presets moves to V83 with 84 presets: 10 new presets, corrected descriptions for the four FLUX 2 8-step presets and the fixed text encoder in the two Qwen Image 2.1 Unified presets; the other 68 presets are unchanged. The new presets need the new FastH3 Omni Core Bundle, the Fibo 2.0 Core Bundle and the updated MOSS-Image Core Bundle of the model downloader.

All 84 presets as they appear in the SwarmUI Presets tab; the new presets are in the last rows:

Every preset still has its own animal. The ten new presets on their own:

Four Fibo 2.0 presets (text to image and image editing, Dev and Turbo), two MOSS Image Edit presets (30 steps and Turbo 8 steps) and four FastH3 Omni presets (references to video, long lip sync, text to image and audio only), each with its own artwork.

Exact V183 → V184 zip audit:

Presets: Amazing_SwarmUI_Presets_v81.json was replaced by Amazing_SwarmUI_Presets_v83.json. Of the 74 presets it keeps, 68 are unchanged in every setting, description and thumbnail; the four FLUX 2 8-step presets have a corrected description and the two Qwen Image 2.1 Unified presets select the fixed text encoder.
9 changed files: the model catalog and its size data (the FastH3 Omni and Fibo 2.0 models and bundles, the MOSS-Image edit LoRA, the Qwen Image 2.1 encoder names and the new source of the MiniMax H3 video VAE), the downloader app (new interface, shows v184), HF_model_downloader.py (keeps files whose header SwarmUI rewrote), update_swarmui.py (the new Fibo2 premium extension), the bundle report generator and the regenerated Which_Bundles_Downloads_Which_Preset_Models.html, and the MOSS-Image and MiniMax H3 prompt guides.
New: the Fibo 2.0 prompt guide in Automatic_Prompt_Generate_Enhance_To_Video_And_Image_Models_LLM_Instructions.
Windows_Install_or_Update_SwarmUI.bat brings SwarmUI with its native Fibo 2.0 support, the new Fibo2 premium extension, MossImage with Image edit mode, MiniMaxH3References 1.21.0, QwenImage21 1.0.2, SECoursesAudioTools and ComfyUI-TeaCache. The ComfyUI backend is updated separately (step 3 of HOW TO UPDATE).

NEW PRESETS — FIBO 2.0: TEXT TO IMAGE AND IMAGE EDITING, DEV AND TURBO

"Fibo 2 Dev - Advanced Text To Image - 261022"

"Fibo 2 Dev - Advanced Image Edit - 261022"

"Fibo 2 Turbo - Image Edit 4 Steps - 261022"

"Fibo 2 Turbo - Text To Image 4 Steps - 261022"

Fibo 2.0 by Bria is an 8B image model that generates and edits images. It was trained on long structured JSON captions that describe every object, the lighting, the camera and the text in the image, so a JSON caption gives the most control; plain text also works. All four presets load the models in INT8 ConvRot with the Qwen3-VL 4B INT8 ConvRot text encoder and the FLUX 2 VAE, set 1024×1024 and turn on our new Fibo2 extension. Measured in SwarmUI on an RTX 5090 at 1024×1024, for a new prompt with the models already loaded:

Dev - Advanced Text To Image: Bria's official recipe: 50 Euler steps, CFG 5 and Bria's JSON negative prompt from the model card. 17.3 seconds per image.
Turbo - Text To Image 4 Steps: Bria made the 4-step Edit Turbo model for editing, but in our tests it also renders text to image very well, lettering included: 4 steps, CFG 1, 1.9 seconds per image.
Dev - Advanced Image Edit: the official editing recipe with 50 steps and CFG 5: 34.7 seconds.
Turbo - Image Edit 4 Steps: Bria's distilled editing model, 4 steps, CFG 1: 2.5 seconds.

About 1 megapixel is the trained size (1024×1024, 1424×800, 1248×832 and the other shapes); 2 megapixels such as 1664×1248 also work well.

Where to find it: Presets tab → type Fibo 2 in the filter → click a preset card → Apply. Its settings fill the new Fibo 2.0 group of the parameters.

Fibo 2 Advanced (on): encodes your prompt with ComfyUI's native Fibo 2.0 text encoder exactly like Bria's pipeline. SwarmUI's generic encoder wraps Fibo 2.0 prompts differently and leaves edit images out of the text encoder.
Fibo 2 Sigma Shift: Bria's official shift, which changes with the image size.
Fibo 2 Edit Size: edits keep the size of the first image from 1 to 4 megapixels.
Editing: attach 1 to 4 images to the prompt with Add Image / Video / Audio (or drag them onto the prompt box) and write the instruction; @image1, @image2 refer to them. Masked edit: an Init Image plus a mask painted in the image editor (white = change).
Prompt syntax: a JSON caption in Bria's format (the new Fibo 2.0 LLM guide writes them for you) or plain text. {red|blue} picks one at random following the seed; (word:1.2) weights are removed because Qwen3-VL would read them as text.
Fibo 2 Prompt List: prompt batches from typed prompts, .txt files or a whole folder (one prompt per file, JSON captions included), like the MOSS-Image prompt batches. Generate prompt batch runs your main prompt first, then every extra prompt.
The extension acts only on Fibo 2.0 models. Apply any other preset and its own workflow runs unchanged.

NEW — ONE JSON PROMPT: FIBO 2 DEV 50 STEPS VS TURBO 4 STEPS

The same JSON caption and seed (261023) through both text-to-image presets. The caption asks for a cafe on a rainy evening with a green sign that reads "MORNING BREW" and a sidewalk chalkboard with "Fresh Coffee" and "Open Late":

Both presets wrote every word as asked, with the warm window light, the wet cobblestones and the guests inside. Turbo needs 1.9 seconds instead of 17.3, which suits trying many prompts; Dev is the full, non-distilled model with CFG and Bria's official recipe, and the model to train LoRAs on.

NEW — ONE PORTRAIT, THREE NEW EDIT PRESETS

A portrait made with Fibo 2 Turbo Text To Image, attached to the prompt as Image 1 and edited with each new edit preset and its default instruction (seed 261023):

Both Fibo 2.0 edits redrew the photo as an anime illustration and kept the pose, the clothes, the coffee cup and the flower shop. MOSS Image Edit replaced the street with a sunny beach and kept the same face, hair, clothes and pose, in 11.1 seconds.

NEW PRESETS — MOSS IMAGE EDIT: EDIT YOUR PHOTOS WITH ONE SENTENCE

"MOSS Image Edit - Advanced Image Edit - 261022"

"MOSS Image Edit - Turbo 8 Steps - 261022"

Both presets use MOSS-Image SFT INT8 ConvRot with ChenkinLab's Moss-Image-Edit LoRA, which the MossImage extension's new Image edit mode adds by itself together with the adapter's reference branch. Attach up to 4 images: image 1 is edited and the others are references, named image 1, image 2 (or @image1, @image2) in the instruction. Say what changes and what stays, for example "Change the background to a sunny beach, preserving the person's identity and pose."

Advanced Image Edit: the official edit recipe: 30 steps, CFG 4, shift 5 and an empty negative prompt. 11.1 seconds at 1024×1024 on an RTX 5090.
Turbo 8 Steps: the community 8-step DMD LoRA at 0.7 with 8 steps and CFG 1: 2.4 seconds. Turbo is close to the 30-step preset in many edits, but for our busy street portrait it kept the street on all five seeds we tried, while the 30-step preset gave a beach on all five. When Turbo ignores a big change such as a new background, use the 30-step preset.
The result has image 1's shape at up to 1024 pixels on the long side (MOSS Image Edit Reference Size; 1536 also works).
Colors, clothes, expressions, lighting, seasons, backgrounds and style edit best. Placing an object from a second image works; copying its exact look is weaker.

Where to find it: Presets tab → type MOSS Image Edit → click a preset card → Apply, then add the photo with Add Image / Video / Audio.

The preset sets MOSS Image Mode to Image edit (attached images). The new MOSS_Image_Edit_LoRA.safetensors (0.28 GB) is part of the updated MOSS-Image Core Bundle.

NEW PRESETS — FASTH3 OMNI: VIDEO WITH AUDIO FROM YOUR REFERENCES IN 8 STEPS

"FastH3 Omni - References to Video 8 Steps - 261022"

"FastH3 Omni - Long Lip Sync - References 8 Steps - 261022"

"FastH3 Omni - Text to Image with Optional References - 261022"

"FastH3 Omni - Audio Only with Optional References - 261022"

FastH3 Omni by FastVideo and Nuva Lab is MiniMax H3's references-to-video-and-audio model distilled to 8 steps. One model makes video with synchronized 32 kHz stereo audio from your prompt plus up to 9 images, 3 videos and 3 audio files, with no turbo LoRA: 8 steps, CFG 1. The presets load it in INT8 ConvRot with the INT8 ConvRot Qwen3-VL 32B text and vision encoder. The References to Video and Long Lip Sync presets also run the sparse attention FastH3 was trained with (VSA): sampling was about 1.4× faster for 5 seconds and 1.9× for 10 seconds of 1344×768 video on an RTX 5090, with the same quality in our tests.

References to Video: 1344×768, 124 frames (5.2 seconds) with audio: 53 to 57 seconds in our runs with one reference image (one run took 108 seconds; we could not find why). It also works as text to video without references.
Long Lip Sync: put the complete soundtrack in Init Audio and a portrait beside the prompt as @image1; one 24 FPS video follows the whole audio in overlapping 8-step windows at 832×1248. About 3.5 minutes for 15 seconds of speech (3.32 minutes in our SwarmUI test).
Text to Image with Optional References: stills from text, or with up to 9 reference images: 9.8 seconds at 1344×768 for a new prompt with one reference image.
Audio Only with Optional References: 32 kHz stereo audio returned as a lossless FLAC: 8 seconds of audio in 7.2 seconds. Put spoken words inside [English] ... .

Where to find it: first Quick Tools → Reset Params to Default, so no MiniMax H3 turbo LoRA from an earlier preset stays selected. Then Presets tab → type FastH3 Omni → click a preset card → Apply, add your images, videos or audio with Add References and mention them in the prompt as @image1, @video1, @audio1.

The prompt describes the woman from @image1 in front of a flower shop: she smiles, raises her coffee cup, greets the viewer with a spoken line in , laughs and takes a sip. Nine frames from the start to the end of the clip:

Her face, curly hair, freckles, earrings and clothes stay those of the portrait in every frame, and the clip follows the prompt from the greeting to the sip. Video and its 32 kHz stereo soundtrack came out of one 8-step run.

NEW — MODEL DOWNLOADER: FASTH3 OMNI AND FIBO 2.0 CORE BUNDLES

FastH3 Omni Core Bundle (49.78 GB, 9 files): FastH3 Omni INT8 ConvRot (20.69 GB), the MiniMax H3 Qwen3-VL 32B INT8 ConvRot text and vision encoder (25.28 GB), the MiniMax H3 video VAE (2.62 GB) and audio VAE (0.56 GB), plus the face models the presets' face refinement and mouth pass use. MiniMax H3 users already have the audio VAE and the face models, and the INT8 ConvRot encoder if they chose it. The video VAE now comes from Comfy-Org, the file SwarmUI itself downloads: if an earlier downloader saved Kijai's copy at the same path, it is replaced once (2.62 GB).
Fibo 2.0 Core Bundle (20.50 GB, 4 files): Fibo 2.0 Dev and Edit Turbo in INT8 ConvRot (7.83 GB each), the Qwen3-VL 4B INT8 ConvRot text encoder (4.52 GB, saved as qwen3vl_4b_int8_convrot.safetensors so it never replaces the qwen3vl_4b.safetensors other models use) and the shared FLUX 2 VAE (0.31 GB).
MOSS-Image Core Bundle (21.91 GB, 7 files): now also downloads MOSS_Image_Edit_LoRA.safetensors (0.28 GB) for the MOSS Image Edit presets.

Where to find it: run Windows_Start_Download_Models_App.bat. The FastH3 Omni Core Bundle and the Fibo 2.0 Core Bundle are the first two bundles of the SwarmUI Bundles tab.

Optional, under Video Generation Models → FastH3 Omni Video Models: FastH3 Omni in BF16 (41.20 GB), FP8 (21.46 GB) and NVFP4 QAD (12.83 GB, for RTX 50 series and other Blackwell GPUs). Under Image Generation Models → Fibo 2.0 Models: both models in BF16 (15.32 GB each), the BF16 text encoder (8.27 GB, saved as qwen3vl_4b.safetensors, the name the FP8 encoder of FLUX 3 Klein and Krea 2 also uses, so keep one precision) and Comfy-Org's Fibo 2.0 turbo LoRA (1.85 GB), which lets Dev and your Dev LoRAs run in 4 steps; the presets do not select it.

NEW — THE DOWNLOADER KEEPS MODELS WHOSE HEADER SWARMUI REWROTE

The first time SwarmUI uses a model, it writes the model hash into the file's header (SwarmUI's ImageMetadataIncludeModelHash setting, on by default). The tensor data stays the same, but the file gets a little larger or its bytes change, so V183 failed its size or SHA-256 check and downloaded the whole model again. V184 reads the original header from Hugging Face, checks your file's tensor data behind it, and keeps the file when every tensor byte matches. A checked file is remembered, so the next run skips it at once.

The log says "[VERIFIED] ... the tensor data matches the Hugging Face file; only the header metadata differs" and "[SKIP] ... already complete". On our test PC, 59 model files with 581 GB in total were a little larger than their Hugging Face files, the sign of SwarmUI's header rewrite. The Fibo 2.0 Core Bundle's four files were checked and kept in 25 seconds instead of downloading 20.50 GB again. Files whose tensor data differs are still downloaded again, as before.

FIXED — SWARMUI NO LONGER DOWNLOADS THE QWEN IMAGE 2.1 TEXT ENCODER AGAIN

Thank you to the supporter who reported this: after the Qwen Image 2.1 Core Bundle, SwarmUI said the text encoder was missing and downloaded it again. The downloader saved the INT8 ConvRot Qwen3-VL 8B encoder as qwen3vl_8b.safetensors, but SwarmUI's native Qwen Image 2.1 support loads qwen3vl_8b_int8_convrot.safetensors; qwen3vl_8b.safetensors is the name SwarmUI uses for its Ideogram 4 encoder. The folder was right: the downloader puts text encoders in the folder SwarmUI's own settings name (Models/text_encoders or Models/clip).

V184 keeps the original names of all three Qwen Image 2.1 text encoders (INT8 ConvRot, BF16 and W4A8). The two Qwen Image 2.1 Unified presets and our QwenImage21 extension 1.0.2 select qwen3vl_8b_int8_convrot, so the presets and plain Qwen Image 2.1 generations share one 8.71 GB file. In our test the downloader got it in 1 min 28 s (1 min 46 s with the SHA-256 check), and SwarmUI then generated with it without downloading anything.

Downloaded with an older version? Older downloaders saved every Qwen Image 2.1 text encoder, and Ideogram 4's too, as qwen3vl_8b.safetensors. Check that file's size in SwarmUI's text encoder folder (Properties shows the bytes; a file SwarmUI has used is about 64 KB larger):

9,350,798,360 bytes: the Qwen Image 2.1 INT8 ConvRot encoder. Rename it to qwen3vl_8b_int8_convrot.safetensors. If SwarmUI already downloaded that file itself, the old one is a spare 8.71 GB copy.
17,534,334,616 bytes: the Qwen Image 2.1 BF16 encoder, rename it to qwen3vl_8b_bf16.safetensors. 6,312,105,364 bytes: the W4A8 encoder, rename it to qwen3vl_8b_w4a8.safetensors.
10,588,637,512 or 6,305,221,764 bytes: Ideogram 4's own FP8 or NVFP4 encoder: keep it.
After a rename, Ideogram 4 gets its own encoder from the Ideogram 4 Core Bundle or SwarmUI's automatic download. The Qwen Image 2.1 Unified presets do not download models, so they need qwen3vl_8b_int8_convrot.safetensors: rename the old file, or run the Qwen Image 2.1 Core Bundle again (it keeps the model and the VAE after checking them).

UPDATED — REDESIGNED, MUCH FASTER MODEL DOWNLOADER

V183 refreshed its status panels through a timer every half second, and after a search or Expand All every refresh blocked the browser for 0.2 to 0.35 seconds. V184 updates only what changed, and search and the precision filter no longer redraw the whole page. Measured in Chrome on our PC with the same catalog, V183 → V184:

Search while typing: results shown about 0.44 seconds after the last key → already shown 0.12 seconds after it.
Clear Search: 673 ms → 10 ms. Expand All: 648 ms → 194 ms.
Precision filter "Display only GGUF models": 851 ms → 11 ms.
Idle page after these steps: busy 65% of the time → 0%.
New look: bundle and model counts in the header, a light / dark switch that your browser remembers, model and bundle cards with an exact size on every file, colored buttons, a colored Activity Log and Active Transfers cards with a progress bar, size, speed and ETA (size and speed also while a file is being checked).
Search shows up to 50 result cards (was 15) with the category, the size or the bundle total; click a card to queue it.
Exact sizes: files below 0.1 GB show in MB, so a 4.8 MB file no longer reads "Size: 0 GB" and counts as unknown in the totals.
The status refresh pauses while the browser tab is hidden; downloads continue. The app's download, queue and cancel logic is unchanged; the only change to file checks is the header check above.

NEW AND UPDATED PROMPT GUIDES FOR LLMS

New: Fibo_2.0_Enchance_Prompt_Feed_For_LLMs.txt. Paste it into ChatGPT, Claude, Gemini or a local LLM, describe the image you want or the edit (attach the images to the LLM chat for an edit), and it returns a JSON caption in Bria's format. Its first part explains how the SwarmUI and ComfyUI presets use the prompt: where it goes, image labels, resolutions and the negative prompt. It is based on Bria's model card and the caption schemas of Bria's own captioning library, plus our tests.
MOSS_Image_Enchance_Prompt_Feed_For_LLMs.txt: new Part 7 for the MOSS Image Edit presets: one short plain-text instruction, the change first and then what stays, and how to name several images.
MiniMax_H3_Enchance_Prompt_Feed_For_LLMs.txt: new FastH3 Omni section: write FastH3 prompts exactly like MiniMax H3 references-to-video prompts.

UPDATED — BUNDLE REPORT AND FLUX 2 PRESET DESCRIPTIONS

Which_Bundles_Downloads_Which_Preset_Models.html is regenerated for V83: all 84 presets, and every new preset is fully covered by its core bundle. The report generator now knows FastH3 Omni's automatic text encoder and VAEs, the edit LoRA that MOSS Image edit mode loads, Qwen Image 2.1's own text encoder and VAE, and shows small files in MB.
The four FLUX 2 8-step presets told you to add --no-cache to the backend arguments for out-of-RAM errors. ComfyUI's argument is --cache-none; their descriptions are corrected.

TESTED — REAL GENERATIONS IN SWARMUI

Every result shown in this post is a real SwarmUI run on 23 October on an RTX 5090 (SwarmUI d74f8ce4, ComfyUI 6cbc3862) after Windows_Install_or_Update_SwarmUI.bat had installed the new extensions and nodes, with the V83 presets imported by Windows_Preset_Delete_Import.bat and applied by real clicks: all four Fibo 2.0 presets, both MOSS Image Edit presets and three FastH3 Omni presets, with seed 261023. The input portrait and four of the five MOSS seed checks ran earlier the same day, before that update. The FastH3 Omni Long Lip Sync preset was tested separately in SwarmUI with a portrait and 15 seconds of speech. The downloader ran from its own bat file: it kept the Fibo 2.0, MOSS-Image, Ideogram 4 and MiniMax H3 files that SwarmUI had rewritten, saved the Qwen Image 2.1 encoder under its own name, and the Qwen Image 2.1 Unified preset then generated without any download in SwarmUI.

CUSTOM NODE PACKS WE DEVELOP OR MAINTAIN UPDATED

SECoursesAudioTools

New Fibo 2.0 nodes for our SwarmUI and ComfyUI Fibo 2.0 presets: prompt and image encoding with ComfyUI's native Fibo 2.0 text encoder (JSON captions encoded like Bria's pipeline, edits keep the first image's size from 1 to 4 MP), Bria's size-dependent shift, and masked edits with ComfyUI's native Mask Editor.
ComfyUI now puts the Fibo 2.0 negative prompt into Bria's chat template itself (22 October), so our nodes no longer wrap it a second time. With the same seed, the four Fibo 2.0 presets give pixel-identical images to before.
New MOSS-Image Edit References node: the reference branch of ChenkinLab's Moss-Image-Edit adapter on ComfyUI's native MOSS-Image model, used by the MOSS Image Edit presets in both apps.
H3 Long Lip Sync without a soundtrack now says that the soundtrack is needed instead of failing with a TypeError.

ComfyUI-TeaCache

The MiniMax H3 Speed Optimizer has a new VSA mode for FastH3 models: ComfyUI's native Video Sparse Attention, used the way FastH3 was trained. Its output is bit-identical to ComfyUI's own VSA node, and sampling is 1.37× (5 seconds) and 1.87× (10 seconds) faster than dense attention at 1344×768 on an RTX 5090.
The default face-pass prompt no longer asks for "beard strands": on a FastH3 Omni image of a woman, the face pass had drawn a beard. Saved workflows keep their own text.

SWARMUI PREMIUM EXTENSIONS UPDATED

Fibo2 1.0.0 (new): Fibo 2 Advanced encoding like Bria's pipeline, Bria's size-dependent shift, automatic edit size (1 to 4 MP), masked edits from Init Image plus mask, the INT8 text encoder as default and prompt batches. It acts only on Fibo 2.0 models. Windows_Install_or_Update_SwarmUI.bat installs it.
MossImage: new Image edit (attached images) mode: it adds the Moss-Image-Edit LoRA and the reference branch, gives the result image 1's reference size, turns @image1 into "image 1" and keeps the attached images out of SwarmUI's text encoder.
MiniMaxH3References 1.21.0: the FastH3 sparse attention choice vsa; when SwarmUI's NVFP4 Qwen3-VL 32B encoder is missing and the INT8 ConvRot encoder of the FastH3 Omni Core Bundle is installed, MiniMax H3 models use it instead of downloading another 14.61 GB file; Audio Only works with FastH3 Omni without a routing warning.
QwenImage21 1.0.2: the Qwen Unified Text Encoder default is qwen3vl_8b_int8_convrot, the file SwarmUI's native Qwen Image 2.1 support loads.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v184.zip from this post and extract it over your existing downloader folder.
Run Windows_Install_or_Update_SwarmUI.bat. It updates SwarmUI to the version with native Fibo 2.0 support (added on 21 October), installs the new Fibo2 premium extension, MossImage with Image edit mode, MiniMaxH3References 1.21.0 and QwenImage21 1.0.2, and updates SECoursesAudioTools and ComfyUI-TeaCache.
Update the ComfyUI backend to its latest version. Fibo 2.0 needs ComfyUI from 21 October or newer and FastH3 Omni from 18 October or newer. With the updated SECoursesAudioTools of step 2, Fibo 2 Dev text to image encodes its negative prompt exactly like Bria's pipeline only on ComfyUI from late 22 October or newer. If SwarmUI uses our ComfyUI installation, update it with our ComfyUI installer V144 (Windows_Install_Or_Update_ComfyUI.bat). If SwarmUI uses its own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start. You can switch it back afterwards. Our ComfyUI installer V144 also brings the same Fibo 2.0, MOSS Image Edit and FastH3 Omni presets and the new prompt guides to ComfyUI.
Restart SwarmUI and its ComfyUI backend so the new extensions and nodes register.
With SwarmUI running, run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v83.json. It backs up your current presets, thumbnails included, to utilities\presets_backups, deletes them all (your own presets too) and imports the new pack.
Run Windows_Start_Download_Models_App.bat and download the FastH3 Omni Core Bundle, the Fibo 2.0 Core Bundle and the MOSS-Image Core Bundle (the files you already have are checked and kept). Qwen Image 2.1 users: see the text encoder fix above.

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709

18 October 2026 Update V183

This is a MOSS-Image update. V183 adds six MOSS-Image presets and our new MossImage premium extension to SwarmUI's new native support for OpenMOSS's MOSS-Image: the official quality recipe, Fast 25 Steps and Turbo 8 Steps presets, two Base model presets, visual layout boxes, JSON layout prompts and prompt batches from .txt files. MOSS-Image renders the text you quote in your prompt, such as shop signs, poster titles and labels. The model downloader gets the MOSS-Image Core Bundle (21.64 GB), the zip adds a MOSS-Image prompt-writing guide for LLMs, and AvatarForever gets live previews and new tested lip motion settings.

Amazing SwarmUI Presets moves to V81 with 74 presets: 6 new MOSS-Image presets, an updated AvatarForever preset and new artwork for the three FLUX 3 Klein presets; the other 64 presets are unchanged. The new presets need the new MOSS-Image Core Bundle (21.64 GB) of the model downloader.

All 74 presets as they appear in the SwarmUI Presets tab; the six MOSS-Image presets are in the last two rows:

The three FLUX 3 Klein presets just before them have new artwork as well (an otter, a flamingo and a meerkat), so every preset has its own animal again. The six new MOSS-Image presets on their own:

Like every other preset, each MOSS-Image preset has its own artwork that shows its task: Text To Image 50 Steps, Fast 25 Steps, Turbo 8 Steps, Layout Boxes, and the Base Model Text To Image and Layout Boxes presets.

NEW PRESETS — MOSS-IMAGE: QUALITY, FAST, TURBO, LAYOUT BOXES AND BASE MODEL

"MOSS Image - Advanced Text To Image - 261017"
"MOSS Image - Fast 25 Steps - 261017"
"MOSS Image - Turbo 8 Steps - 261017"
"MOSS Image - Advanced Layout Boxes - 261017"
"MOSS Image Base - Advanced Text To Image - 261018"
"MOSS Image Base - Advanced Layout Boxes - 261018"

All six load MOSS-Image in INT8 ConvRot with SwarmUI's own Qwen3.5 9B INT8 ConvRot text encoder and the FLUX 2 VAE, set 1024×1024 and turn on our MossImage extension. MOSS-Image is a 5B single-stream image model that reads plain language, tags or JSON layouts, with prompts up to about 4K tokens. Measured in SwarmUI on an RTX 5090 at 1024×1024, for a new prompt with the models already loaded:

Advanced Text To Image: the official quality recipe (50 Euler steps, normal scheduler, CFG 3, shift 5, negative-branch skip of layer 22 and the official negative tags) plus PyTorch attention and the SFT de-band fix. 12.9 seconds per image.
Fast 25 Steps: 25 ER-SDE steps with Score Rescaling 0.95 and layers 22 and 24 skipped from 10% to 70% of sampling: 6.9 seconds, nearly twice as fast. Large lettering held up in our tests; small text can get an occasional misspelling.
Turbo 8 Steps: the community 8-step DMD LoRA (lodestones, Apache-2.0) at 0.7 with 8 Euler steps and CFG 1: 1.8 seconds per image. The LoRA is a work in progress, so its images differ more from the official model and can show stray small text.
Advanced Layout Boxes: the official recipe with visual layout boxes, ready with three example boxes.
Base - Advanced Text To Image and Base - Advanced Layout Boxes: the raw Base model with the official 50-step recipe (13.0 seconds for Base Text To Image). Base gives more varied images and is the model that LoRAs trained on Base expect; SFT gives clearer text grouping and layouts. With the same seed, 80 steps gave no visible gain over 50 in our tests, so the Base presets keep 50. There is no Base Turbo preset, because the 8-step LoRA was trained on SFT.

Where to find it: Presets tab → type MOSS Image in the filter → click a preset card → Apply. Its settings fill the new MOSS-Image group of the parameters.

The MOSS-Image group and the preset settings in detail:

Seed: -1 gives a new image every time; a fixed seed repeats the same image (pixel-identical in our tests).
Mode: Text / JSON prompt or Layout boxes.
Negative Skip Layers (22): the official skip-layer guidance; the negative branch runs without these layers. Skip Start / End limit it to part of sampling. It needs CFG above 1.
Attention (PyTorch): with PyTorch attention the INT8 ConvRot files gave images close to the official BF16 outputs. Setting it here also protects the BF16 files, which gave black images with a --use-sage-attention backend in our RTX 3090 tests.
Score Rescaling (1 is off): the Fast preset uses 0.95; lower values give more detail, higher values smoother images.
SFT De-Band (on): MOSS-Image SFT draws faint vertical color stripes on skies, fog, walls and backdrops. The fix loads MATLOWAI's de-band LoRA (Apache-2.0, in the MOSS-Image Core Bundle) for SFT models only; Base models never get it.
Your usual SwarmUI controls keep working: resolution, batch size, variation seed and LoRAs. 1 to 2 megapixel resolutions are recommended.
The extension acts only on MOSS-Image models. Apply any other preset and its own workflow runs unchanged.

NEW — ONE PROMPT, FOUR PRESETS: QUALITY, SPEED AND THE BASE MODEL

The same prompt and seed (261018) through four of the new presets. The prompt asks for a bookshop on a rainy evening with a sign that reads "THE LAST CHAPTER", a chalkboard that says "New arrivals / Hot tea inside", a sleeping orange cat in the window and string lights:

All four rendered the sign and the chalkboard text as written, with the sleeping cat in the window. Fast needs about half the time of the 50-step preset, and Turbo returns an image in 1.8 seconds, which suits trying many prompts. The 50-step presets are the most faithful; Base gives its own, more varied take on the same prompt.

NEW — VISUAL LAYOUT BOXES: PUT TEXT AND OBJECTS WHERE YOU WANT THEM

Choose Layout boxes mode, draw boxes on a canvas that has the shape of your output image and describe each box. The main prompt becomes the overall image caption. The extension builds the layout with ComfyUI's native MOSS-Image layout nodes, so the model places each box's content where you drew it.

Draw a box with the mouse and drag it to move it; select a box and drag its lower-right corner to resize it.
Each box is an Object, Character or Text / lettering box. Text boxes render their exact text, line breaks included, and every edge can be typed in percent.
Add, delete and reorder up to 32 boxes, or open the JSON.
Boxes guide the composition; they are not inpainting masks.

Where to find it: apply the MOSS Image - Advanced Layout Boxes preset or its Base version. The canvas is in the MOSS-Image group.

The preset's three boxes put the title "EXPLORE THE ALPS" at the top, the mountain lake illustration in the middle and the subtitle "Summer 2026 | Lakes, trails and fresh air" at the bottom, as drawn, in 13.5 seconds of generation time.

NEW — PROMPT SYNTAX AND JSON LAYOUT PROMPTS

MOSS-Image reads the prompt with Qwen3.5 as plain language, tags or JSON. Long, specific prompts work best; put the text that must appear in the image in quotes and use real line breaks to control its lines.
{red|blue} picks one at random, following the seed.
[red:blue:0.5] switches from one word to the other halfway through sampling, and [red|blue] alternates them from step to step.
(word:1.2) weights are removed, because Qwen3.5 would read them as literal text; describe emphasis in words instead. Times and ratios such as (10:30) or (4:3) stay.
A complete JSON layout passes through unchanged, and pixel drafts from the official MOSS-Image prompt enhancer are converted to the model's own box format at your output size. SwarmUI's own prompt tags keep working.

NEW — PROMPT BATCHES FROM .TXT FILES OR A WHOLE FOLDER

Generate a series with the same settings. Add prompt adds a prompt you type; Import .txt and Import folder load text files, one complete prompt per file, JSON layouts included. Generate prompt batch runs your main prompt first and then every extra prompt; Stop after current ends the batch after the current prompt finishes. The normal Generate button still generates only the main prompt.

Where to find it: MOSS-Image group → MOSS Image Prompt List, in every MOSS-Image preset.

Three imported .txt files plus the main prompt gave four images with the Turbo 8 Steps preset in 7.4 seconds, from click to finish: the bookshop, a "COASTAL ESCAPE" travel poster, a "MORNING RITUAL" coffee cup and a sleeping fox. A batch takes up to 63 extra prompts. If a preset is only selected and not applied, the batch asks you to apply it first, so the preset's own prompt cannot replace your batch prompts.

NEW — MODEL DOWNLOADER: MOSS-IMAGE CORE BUNDLE (21.64 GB)

One click downloads everything the six presets use:

moss_image_sft_int8_convrot.safetensors (5.04 GB): the quality fine-tuned SFT model, the preset default.
moss_image_base_int8_convrot.safetensors (5.04 GB): the raw Base model for the Base presets, LoRA training and variety.
Qwen3.5 9B INT8 ConvRot text encoder (9.08 GB), saved as qwen3.5_9b_int8_convrot.safetensors, the file and name SwarmUI itself downloads for MOSS-Image, so SwarmUI reuses it.
FLUX 2 VAE (0.31 GB), saved as VAE/Flux/flux2-vae.safetensors, the same file FLUX 2 Klein and FLUX 3 Klein use.
MOSS_Image_SFT_DeBand_L37-41.safetensors (1.05 GB, MATLOWAI, Apache-2.0): the SFT banding fix that the presets apply automatically.
MOSS_Image_SFT_8_Steps_DMD_LoRA.safetensors (1.11 GB, lodestones, Apache-2.0): the 8-step LoRA of the Turbo preset, saved from lodestones' latest release file, which can change upstream.

Where to find it: run Windows_Start_Download_Models_App.bat. The MOSS-Image Core Bundle is the first bundle of the SwarmUI Bundles tab.

Optional, under Image Generation Models → MOSS-Image Models: the original BF16 SFT and Base models (9.47 GB each; BF16 Base is the recommended precision for LoRA training and fine-tuning), a smaller Qwen3.5 9B W4A8 GPTQ text encoder for low RAM and VRAM (6.84 GB; select it in the Qwen Model parameter), the FLUX 2 small-decoder VAE that decodes faster with less VRAM (0.23 GB; select it as the VAE) and an extra banding fix for stubborn smooth skies (1.05 GB).

Why INT8 ConvRot with PyTorch attention: on an RTX 3090 the INT8 ConvRot files run about twice as fast as BF16, and with PyTorch attention their images were close to the official BF16 outputs. The INT8 files' own INT8 attention is about 20% faster, but it changed the images noticeably in our tests, so the presets use PyTorch attention. Our ComfyUI graph with these settings reproduced official MOSS-Image Space examples from the same seed, with the same composition, subject and details.

UPDATED — AVATARFOREVER: LIVE PREVIEWS, TESTED LIP MOTION SETTINGS AND A HISTORY FIX

Live previews: the AvatarForever sampler now shows a preview frame after every denoising step, starting at step 1, and the finished video after export; in SwarmUI the previews appear in the normal generation preview. They use taeltx2_3.safetensors (0.02 GB) when you have it, now part of the LTX 2.3 Avatar Forever Core Bundle (44.53 GB), and a fast latent preview otherwise. Previews do not change the video: with previews on and off, the same 452-frame MP4 came out byte for byte in our test.
Tested lip motion settings: the AvatarForever Unified Image + Audio or Text + Audio preset now renders an exact 512×768 portrait canvas with 16 latent frames per chunk (was 4) and a prompt that asks for expressive mouth movement. In a six-second comparison with the same portrait, song, prompt and seed, 4-frame chunks kept the lips closed and 16-frame chunks gave visible mouth movement, which held through the complete 18-second song. At 1024×1024 the mouth stayed mostly closed in the same test even with 16-frame chunks, so the preset keeps 512×768. Larger chunks use more memory; check a short sample when you change the image, the audio or the resolution.
History fix (AvatarForever 1.0.3): an interrupted video export could leave an incomplete MP4 that kept SwarmUI's History waiting, and with several browser tabs open even finished images stopped loading. SwarmUI now skips the metadata of such files; complete files and generation settings are unchanged.

Where to find it: Presets tab → type AvatarForever → click the preset card → Apply, then attach a speech or song to the prompt and, if you like, a portrait as Init Image.

NEW — MOSS-IMAGE PROMPT GUIDE FOR LLMS

New file: Automatic_Prompt_Generate_Enhance_To_Video_And_Image_Models_LLM_Instructions/MOSS_Image_Enchance_Prompt_Feed_For_LLMs.txt. Give it to ChatGPT, Claude, Gemini or a local LLM together with your idea, and it writes MOSS-Image prompts: detailed captions, exact text for signs and posters, and layout drafts with boxes that the presets convert to MOSS-Image's own coordinates at your output size. Its first part explains how the SwarmUI and ComfyUI presets use the prompt (recipe, prompt syntax, layout mode and resolutions); it is based on the official MOSS-Image user guide and its prompt enhancer.

UPDATED — BUNDLE REPORT AND DOWNLOADER APP

Which_Bundles_Downloads_Which_Preset_Models.html is regenerated for V81: all 74 presets, and every MOSS-Image preset is fully covered by the MOSS-Image Core Bundle. The report generator now knows SwarmUI's default MOSS-Image text encoder and VAE, the de-band LoRA that the MossImage extension loads by itself for SFT models, and AvatarForever's live-preview file.
Windows_Start_Download_Models_App.bat now installs the downloader's packages in pip's isolated mode, so your user pip configuration and PIP_ option variables no longer affect its install.
The downloader app shows v183.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v183.zip from this post and extract it over your existing downloader folder.
Run Windows_Install_or_Update_SwarmUI.bat. It updates SwarmUI to the version with native MOSS-Image support (added on 17 October), installs the new MossImage premium extension and AvatarForever 1.0.3, and updates SECoursesAudioTools.
Update the ComfyUI backend: MOSS-Image needs ComfyUI from 16 October or newer. If SwarmUI uses our ComfyUI installation, update it with our ComfyUI installer V143 (Windows_Install_Or_Update_ComfyUI.bat). If SwarmUI uses its own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start. You can switch it back afterwards. Our ComfyUI installer V143 also brings the same six MOSS-Image presets and the MOSS-Image prompt guide to ComfyUI.
Restart SwarmUI and its ComfyUI backend so the new extension and nodes register.
With SwarmUI running, run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v81.json. It backs up your current presets, thumbnails included, to utilities\presets_backups, deletes them all (your own presets too) and imports the new pack.
Run Windows_Start_Download_Models_App.bat and download the MOSS-Image Core Bundle. AvatarForever users: also download taeltx2_3.safetensors (0.02 GB) for the live previews; it is in the LTX 2.3 Avatar Forever Core Bundle and under Video Generation Models → LTX 2.3 Video Models.

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709

16 October 2026 Update V182

This is a FLUX 3 Klein update. V182 brings Black Forest Labs' new FLUX 3 Klein image model to SwarmUI with three advanced presets and our new FLUX 3 Klein premium extension: text to image, image editing with up to 10 reference images, visual layout boxes, ComfyUI-style prompt syntax and prompt batches from .txt files. The model downloader gets the FLUX 3 Klein Core Bundle with our HQ INT8 ConvRot model (10.85 GB in total), and the zip adds a FLUX 3 Klein prompt-writing guide for LLMs.

Amazing SwarmUI Presets moves to V80 with 68 presets: 3 new FLUX 3 Klein presets, and the other 65 presets are unchanged. The new presets need the new FLUX 3 Klein Core Bundle (10.85 GB) of the model downloader.

All 68 presets as they appear in the SwarmUI Presets tab; the three FLUX 3 Klein presets are in the last row:

Like every other preset, each FLUX 3 Klein preset has its own artwork that shows its task: Text To Image, Image Edit or Layout Boxes.

NEW PRESETS — FLUX 3 KLEIN: TEXT TO IMAGE, IMAGE EDIT AND LAYOUT BOXES

"FLUX 3 Klein - Advanced Text To Image - 261015"

"FLUX 3 Klein - Advanced Image Edit - 261015"

"FLUX 3 Klein - Advanced Layout Boxes - 261015"

All three load our HQ INT8 ConvRot FLUX 3 Klein model with SwarmUI's own Qwen3-VL 4B text encoder and the FLUX 2 VAE, and set 1024×1024, 16 steps, Euler/simple and CFG 1 (CFG 1 ignores the negative prompt). Each preset turns on our FLUX 3 Klein extension in its own mode: Text / optional references, Reference edit or Layout / optional references. Measured in SwarmUI on an RTX 5090 at 1024×1024: about 2 seconds of generation time for an image and 3.9 seconds for an edit with one reference image.

Where to find it: Presets tab → type FLUX 3 Klein in the filter → click a preset card → Apply. Its settings fill the new FLUX.3 Klein group of the parameters.

The FLUX.3 Klein group and the preset settings in detail:

Seed: -1 gives a new image every time; a fixed seed repeats the same image (pixel-identical in our tests).
Mode: text to image, reference edit or layout boxes. Reference images are optional in the text and layout modes.
Reference Megapixels: the size of each attached image, from 0.1 to 4 megapixels (1 is about 1024×1024), independent of the output size.
Your usual SwarmUI controls keep working: resolution, batch size, variation seed and compatible FLUX 3 Klein LoRAs.
The extension acts only on FLUX 3 Klein models. Apply any other preset and its own workflow runs unchanged.

NEW — EDIT IMAGES WITH UP TO 10 REFERENCE IMAGES (@image1, @image2)

Attach images to the prompt with Add Image / Video / Audio and cite them in your prompt: @image1 is the first attachment, @image2 the second, and so on (@img1, @picture1 and @pic1 work too). Describe the complete result: what changes and what stays. The extension turns these names into FLUX 3 Klein's own reference labels.

Up to 10 images. Each keeps its aspect ratio, and transparent areas are filled with white.
Reference edit needs at least one image. If the prompt cites an image that is not attached, SwarmUI shows a clear error; video and audio attachments are refused with a message.

Where to find it: apply the FLUX 3 Klein - Advanced Image Edit preset, attach your photo above the prompt and describe the result.

Here the white mug of the attached photo became cobalt blue in 3.9 seconds of generation time, while the croissant, the window, the light and the camera angle stayed. To take one object out of several references, name the image it comes from and say which other objects should be absent: in our test with this coffee photo as @image1 and a red teapot as @image2, asking for the vessel from @image2 gave the teapot alone.

NEW — VISUAL LAYOUT BOXES: PUT EVERY OBJECT WHERE YOU WANT IT

Draw boxes on a canvas that has the shape of your output image, describe the object of each box, and cite the boxes in your prompt as , . SwarmUI turns them into FLUX 3 Klein's native layout table, so the model places each object in its box.

Draw a box with the mouse and drag it to move it; select a box and drag its lower-right corner to resize it.
Each box is an Object or Text / lettering with the exact text to render, and its edges can be typed in percent.
Add, delete and reorder up to 32 boxes, or open the JSON. Reference images still work in this mode.
Boxes guide the composition; they are not inpainting masks.

Where to find it: apply the FLUX 3 Klein - Advanced Layout Boxes preset. The canvas is in the FLUX.3 Klein group.

The preset's two boxes put the red teapot on the left and the blue cup on the right, as drawn, in 2.0 seconds of generation time.

NEW — COMFYUI-STYLE PROMPT SYNTAX

The FLUX 3 Klein presets understand the prompt syntax of our ComfyUI presets, next to SwarmUI's own prompt tags:

(ceramic:1.1) weights a phrase.
[red:blue:0.5] switches from one word to the other halfway through sampling.
[red|blue] alternates the words from step to step.
splits the prompt into separately encoded parts.
{red|blue} picks one at random, following the seed.
SwarmUI tags such as random:red|blue, and alternate:red|blue keep working.
A complete native caption with its JSON layout table, as the new prompt guide writes it, works in the text and reference edit modes.

NEW — PROMPT BATCHES FROM .TXT FILES OR A WHOLE FOLDER

Generate a series with the same settings and reference images. Add prompt adds a prompt you type; Import .txt and Import folder load text files, one complete prompt per file, in natural file-name order. Generate prompt batch runs your main prompt first and then every extra prompt; Stop after current ends the batch after the current prompt finishes. The normal Generate button still generates only the main prompt.

Where to find it: FLUX.3 Klein group → FLUX Klein Prompt List, in every FLUX 3 Klein preset.

Three imported .txt files plus the main prompt gave four images in 8 seconds, from click to finish. A batch takes up to 63 extra prompts.

NEW — MODEL DOWNLOADER: FLUX 3 KLEIN CORE BUNDLE (10.85 GB)

One click downloads everything the three presets use:

FLUX-3-Image-Klein-INT8-ConvRot-HQ.safetensors (5.66 GB): our HQ INT8 ConvRot version of the distilled FLUX 3 Klein, with selected layers kept in BF16.
Qwen3-VL 4B FP8 text encoder (4.88 GB), saved as qwen3vl_4b.safetensors, the file name SwarmUI itself uses for FLUX 3 Klein.
FLUX 2 VAE (0.31 GB), saved as VAE/Flux/flux2-vae.safetensors, the same file FLUX 2 Klein uses: if you already have it, it is verified and skipped.

Where to find it: run Windows_Start_Download_Models_App.bat. The FLUX 3 Klein Core Bundle is the first bundle of the SwarmUI Bundles tab.

Optional, under Image Generation Models → FLUX 3 Klein Models: the original distilled BF16 model (10.34 GB), the undistilled Base BF16 checkpoint for fine-tuning and LoRA training (10.32 GB; it uses its own 50-step, guidance 3.5 settings), and a Qwen3-VL 4B BF16 text encoder (8.27 GB). The BF16 encoder has the same qwen3vl_4b.safetensors name as the FP8 one, so download only one of them.

Why HQ INT8: in our 40-state test against the original BF16 model (BF16 text encoder, RTX 3090), the denoiser output of our HQ INT8 ConvRot model differed by 2.14% on average, against 3.05% for the official INT8 ConvRot file with its default settings and 2.27% with matched attention; with matched attention, one held-out edit case favored the official file (3.84% against 3.58%; 4.73% with its default settings). The transformer peaked at about 6 GiB of VRAM instead of 10.5 GiB and ran each step about twice as fast as BF16. These are numerical-fidelity measurements, not image-quality percentages.

UPDATED — TEXT ENCODERS GO WHERE YOUR SWARMUI LOOKS FOR THEM

SwarmUI keeps text encoders in the folders of its SDClipFolder setting: text_encoders;clip on installs from late November 2025 on, and only clip on older installs, because SwarmUI never changes a setting it has saved. The downloader now reads this setting from your SwarmUI (Data/Settings.fds next to the Models folder you download into):

A text encoder you already have in one of those folders is verified where it is, instead of being downloaded a second time.
A new text encoder goes into the first folder, where SwarmUI saves its own downloads too.
If the downloader cannot find your SwarmUI settings, it uses clip, which SwarmUI scans by default on every install.

The ComfyUI and Forge folders are unchanged. We tested this on new, old and custom SwarmUI folder settings.

NEW — FLUX 3 KLEIN PROMPT GUIDE FOR LLMS

New file: Automatic_Prompt_Generate_Enhance_To_Video_And_Image_Models_LLM_Instructions/FLUX_3_Klein_Enchance_Prompt_Feed_For_LLMs.txt. Give it to ChatGPT, Claude, Gemini or a local LLM together with your idea, and it writes FLUX 3 Klein prompts: text-to-image captions, edits that say what stays and what changes, multi-reference prompts with @image1 and @image2, exact text for posters and signs, and layout boxes. Its first part explains the SwarmUI presets (modes, @image numbering, the box editor, prompt syntax and batches); the rest is the same research-based guide, version 1.5, as in our ComfyUI installer, with original examples.

UPDATED — BUNDLE REPORT, PRESET BACKUPS AND DOWNLOADER APP

Which_Bundles_Downloads_Which_Preset_Models.html is regenerated for V80: all 68 presets, and the three FLUX 3 Klein presets are fully covered by the FLUX 3 Klein Core Bundle. The report generator now also knows SwarmUI's default FLUX 3 Klein text encoder and VAE.
Preset backups keep their thumbnails: Windows_Preset_Delete_Import.bat now saves every preset's thumbnail inside the backup file, so a backup holds everything needed to bring your own presets back with their images.
The downloader app shows v182 and uses Gradio 6.30.0. Windows_Start_Download_Models_App.bat updates Gradio automatically, and the RunPod / SimplePod and Massed Compute instructions install it.

TESTED — REAL GENERATIONS IN CHROME

The extension and the presets were tested on 15 October with SwarmUI 967f005c and ComfyUI 20b46065 on an RTX 5090 in a real Chrome: text to image, scene-preserving edits, two-reference selection, visual layout (drawing, moving and resizing boxes), advanced prompt syntax, prompt batches, .txt file and folder import, Stop after current, and 23 workflow checks (reference numbering, the 10-image limit, duplicate images, layout tables, reference sizing and model gating). Every generated result shown in this post is a real run on the HQ INT8 model. The optional BF16 models and FLUX 3 Klein LoRAs were not generated separately.

CUSTOM NODE PACKS WE DEVELOP OR MAINTAIN UPDATED

SECoursesAudioTools

LoRA and DoRA files trained with SECourses Musubi Trainer now load completely. ComfyUI silently skipped some of their layers: the MLP halves of Qwen Image 2.1, the q, k and v parts of Z-Image's fused attention, and every HiDream-O1 layer. The node pack now maps the trainer's layer names to them, DoRA scales included. SwarmUI gets this too: Windows_Install_or_Update_SwarmUI.bat installs this node pack for SwarmUI's self-starting ComfyUI backend.
New FLUX.3 Gallery Prompt and FLUX.3 Optional Gallery References nodes connect our reference gallery to FLUX 3 Klein in our ComfyUI presets: @image1 names, seeded {red|blue} choices and up to 10 references with their own size.

SWARMUI PREMIUM EXTENSIONS UPDATED

FluxThreeKlein 1.0.0 (new): FLUX 3 Klein advanced prompting, image references, visual layout boxes and prompt batches on SwarmUI's native FLUX 3 workflow. Windows_Install_or_Update_SwarmUI.bat installs it.

HOW TO UPDATE

Download SwarmUI_Model_Downloader_v182.zip from this post and extract it over your existing downloader folder.
Run Windows_Install_or_Update_SwarmUI.bat. It updates SwarmUI to the version with native FLUX 3 Klein support (added on 15 October), installs the new FluxThreeKlein premium extension and updates SECoursesAudioTools.
Update the ComfyUI backend: FLUX 3 Klein needs ComfyUI from 15 October or newer (tested with 20b46065). If SwarmUI uses our ComfyUI installation, update it with our ComfyUI installer V141 (Windows_Install_Or_Update_ComfyUI.bat). If SwarmUI uses its own ComfyUI, open Server → Backends, edit the ComfyUI Self-Starting backend and set AutoUpdate to Always Update for one start. You can switch it back afterwards.
Restart SwarmUI and its ComfyUI backend so the new extension and nodes register.
With SwarmUI running, run Windows_Preset_Delete_Import.bat to import Amazing_SwarmUI_Presets_v80.json. It backs up your current presets, thumbnails included, to utilities\presets_backups, deletes them all (your own presets too) and imports the new pack.
Run Windows_Start_Download_Models_App.bat and download the FLUX 3 Klein Core Bundle.

ComfyUI Installer and Presets: https://www.patreon.com/posts/105023709