DEV Community

AI-KSK profile picture

AI-KSK

AI creator focused on ComfyUI, AI video generation, workflows and practical AIGC tutorials. Sharing reproducible workflows, model tests and YouTube guides.

Joined Joined on 
Qwen 2511 Masked Repaint: Crop the Masked Block, Edit with a Reference, Paste It Back Seamlessly
ai-ksk profile
AI-KSK

Qwen 2511 Masked Repaint: Crop the Masked Block, Edit with a Reference, Paste It Back Seamlessly

#comfyui #ai #tutorial
Comments
3 min read
InfiniteTalk Goes Native in ComfyUI: Single and Dual Lip-Sync Loops, Plus the LTX-2 Distilled Route
ai-ksk profile
AI-KSK

InfiniteTalk Goes Native in ComfyUI: Single and Dual Lip-Sync Loops, Plus the LTX-2 Distilled Route

#comfyui #ai #tutorial
Comments
4 min read
LTX-2 Adapter LoRA: Image-to-Video Consistency at 60fps, Distilled vs Full-Quality Graphs
ai-ksk profile
AI-KSK

LTX-2 Adapter LoRA: Image-to-Video Consistency at 60fps, Distilled vs Full-Quality Graphs

#comfyui #ai #tutorial
Comments
3 min read
LTX-2 Rapid Merge: Uncensored Merged Model, Updated Adapter LoRA, Four Workflows in One Image
ai-ksk profile
AI-KSK

LTX-2 Rapid Merge: Uncensored Merged Model, Updated Adapter LoRA, Four Workflows in One Image

#comfyui #ai #tutorial
Comments
3 min read
Qwen-Image-Edit 2511 + VNCCS Pose Studio: Pose and Lighting Control Without Opening a 3D App
ai-ksk profile
AI-KSK

Qwen-Image-Edit 2511 + VNCCS Pose Studio: Pose and Lighting Control Without Opening a 3D App

#comfyui #ai #tutorial
Comments
3 min read
Seedance 2.0 Post-Production in ComfyUI: Watermark Removal, GIMM Frame Interpolation, FlashVSR Upscale
ai-ksk profile
AI-KSK

Seedance 2.0 Post-Production in ComfyUI: Watermark Removal, GIMM Frame Interpolation, FlashVSR Upscale

#comfyui #ai #tutorial
Comments
3 min read
Anima 2B: An Anime Model Trained Without a Single AI-Generated Image, From Text-to-Image to Tiled Upscale
ai-ksk profile
AI-KSK

Anima 2B: An Anime Model Trained Without a Single AI-Generated Image, From Text-to-Image to Tiled Upscale

#comfyui #ai #tutorial
Comments
3 min read
Z-Image Base + ControlNet 2.1 + Turbo: Two-Stage Repair, and Why the 8/4-Step Accelerators Are a Bad Trade
ai-ksk profile
AI-KSK

Z-Image Base + ControlNet 2.1 + Turbo: Two-Stage Repair, and Why the 8/4-Step Accelerators Are a Bad Trade

#comfyui #ai #tutorial
Comments
4 min read
Z-Image i2L in ComfyUI: A Reusable LoRA From 6 Images in Seconds, Then a ControlNet Pass
ai-ksk profile
AI-KSK

Z-Image i2L in ComfyUI: A Reusable LoRA From 6 Images in Seconds, Then a ControlNet Pass

#comfyui #ai #tutorial
Comments
4 min read
The Last Step Nobody Automates: Batch Frame Interpolation and Upscaling to 4K120
ai-ksk profile
AI-KSK

The Last Step Nobody Automates: Batch Frame Interpolation and Upscaling to 4K120

#comfyui #ai #tutorial
Comments
4 min read
BitDance 14B: A 14-Billion-Parameter Autoregressive Image Model That Is Actually Fast
ai-ksk profile
AI-KSK

BitDance 14B: A 14-Billion-Parameter Autoregressive Image Model That Is Actually Fast

#comfyui #ai #tutorial
Comments
3 min read
FireRed Image Edit 1.0 vs Qwen 2511: Five Single-Image Edits, Two Graphs, One Honest Verdict
ai-ksk profile
AI-KSK

FireRed Image Edit 1.0 vs Qwen 2511: Five Single-Image Edits, Two Graphs, One Honest Verdict

#comfyui #ai #tutorial
Comments
4 min read
SkyReels V3 R2V x VACE Merge: Skeleton-Driven Character Video With a Stronger Reference
ai-ksk profile
AI-KSK

SkyReels V3 R2V x VACE Merge: Skeleton-Driven Character Video With a Stronger Reference

#comfyui #ai #tutorial
Comments
4 min read
Face Swap on Flux 2 Klein 9B: Mask-Guided LanPaint, a Rank-128 BFS LoRA, and a Megapixel Budget
ai-ksk profile
AI-KSK

Face Swap on Flux 2 Klein 9B: Mask-Guided LanPaint, a Rank-128 BFS LoRA, and a Megapixel Budget

#comfyui #ai #tutorial
Comments
4 min read
Writing Your Own ComfyUI Node With VS Code, Cline and Doubao Seed 2.0 Code
ai-ksk profile
AI-KSK

Writing Your Own ComfyUI Node With VS Code, Cline and Doubao Seed 2.0 Code

#comfyui #ai #tutorial
Comments
3 min read
Five Character-Animation Workflows in One ComfyUI Image: Wan Animate 2.2, SCAIL, SteadyDancer, OneToAll, VACE Phantom
ai-ksk profile
AI-KSK

Five Character-Animation Workflows in One ComfyUI Image: Wan Animate 2.2, SCAIL, SteadyDancer, OneToAll, VACE Phantom

#comfyui #ai #tutorial
Comments
4 min read
LTX 2.3 Without the Guesswork: 7 ComfyUI Graphs, 8 Steps vs 15, and Why Non-Accelerated Wins for Text-to-Video
ai-ksk profile
AI-KSK

LTX 2.3 Without the Guesswork: 7 ComfyUI Graphs, 8 Steps vs 15, and Why Non-Accelerated Wins for Text-to-Video

#comfyui #ai #tutorial
Comments
5 min read
Training a Qwen-Image-2512 Face LoRA in AI Toolkit: 3,000 Steps, Rank 64, Batch 1
ai-ksk profile
AI-KSK

Training a Qwen-Image-2512 Face LoRA in AI Toolkit: 3,000 Steps, Rank 64, Batch 1

#comfyui #ai #tutorial
Comments
5 min read
Z-Image Turbo: enhanced text encoder + Flow-DPO + Ultra Real, tested at a fixed seed
ai-ksk profile
AI-KSK

Z-Image Turbo: enhanced text encoder + Flow-DPO + Ultra Real, tested at a fixed seed

#comfyui #ai #tutorial
Comments
4 min read
Running OpenClaw against a local Ollama model: what to check before you download 20 GB
ai-ksk profile
AI-KSK

Running OpenClaw against a local Ollama model: what to check before you download 20 GB

#comfyui #ai #tutorial
Comments
3 min read
LTX 2.3 multi-image first/last frame at 20 images, plus IC-LoRA Union video control
ai-ksk profile
AI-KSK

LTX 2.3 multi-image first/last frame at 20 images, plus IC-LoRA Union video control

#comfyui #ai #tutorial
Comments
4 min read
Anima Preview 2 in ComfyUI: four graphs, one enhancement node, and a conflict worth flagging
ai-ksk profile
AI-KSK

Anima Preview 2 in ComfyUI: four graphs, one enhancement node, and a conflict worth flagging

#comfyui #ai #tutorial
Comments
4 min read
LTX 2.3 three-stage sampling: correct as you upscale, and why every pass re-injects the image
ai-ksk profile
AI-KSK

LTX 2.3 three-stage sampling: correct as you upscale, and why every pass re-injects the image

#comfyui #ai #tutorial
Comments
4 min read
Multi-image first/last frame with LTX 2.3 three-stage sampling: 4 images, 241 frames, 3 real steps
ai-ksk profile
AI-KSK

Multi-image first/last frame with LTX 2.3 three-stage sampling: 4 images, 241 frames, 3 real steps

#comfyui #ai #tutorial
Comments
4 min read
LTX 2.3 digital human in three passes — and the honest case for keeping LTX 2 around
ai-ksk profile
AI-KSK

LTX 2.3 digital human in three passes — and the honest case for keeping LTX 2 around

#comfyui #ai #tutorial
Comments
4 min read
Colorizing black-and-white video with LTX 2.3 IC-LoRA: one reference frame, no preprocessor
ai-ksk profile
AI-KSK

Colorizing black-and-white video with LTX 2.3 IC-LoRA: one reference frame, no preprocessor

#comfyui #ai #tutorial
Comments
4 min read
Fish Audio S2 Pro + LTX 2.3: from zero-shot voice clone to a talking digital human
ai-ksk profile
AI-KSK

Fish Audio S2 Pro + LTX 2.3: from zero-shot voice clone to a talking digital human

#comfyui #ai #tutorial
Comments
4 min read
Eight LTX 2.3 workflows in one image: face swap, ID LoRA, digital human, repaint, multi-image keys
ai-ksk profile
AI-KSK

Eight LTX 2.3 workflows in one image: face swap, ID LoRA, digital human, repaint, multi-image keys

#comfyui #ai #tutorial
Comments
4 min read
Training an LTX 2.3 LoRA with AI Toolkit: the parameter set that actually matters
ai-ksk profile
AI-KSK

Training an LTX 2.3 LoRA with AI Toolkit: the parameter set that actually matters

#comfyui #ai #tutorial
Comments
4 min read
Wan 2.2 Remix 3.0 and SmoothMix 3.0 in ComfyUI: uncensored merges, and a negative prompt that survives CFG 1
ai-ksk profile
AI-KSK

Wan 2.2 Remix 3.0 and SmoothMix 3.0 in ComfyUI: uncensored merges, and a negative prompt that survives CFG 1

#comfyui #ai #tutorial
Comments
4 min read
Pinning down LTX 2.3 with the VBVR reasoning LoRA: same seed, one variable
ai-ksk profile
AI-KSK

Pinning down LTX 2.3 with the VBVR reasoning LoRA: same seed, one variable

#comfyui #ai #tutorial
Comments
4 min read
Multi-image first/last-frame transitions in LTX 2.3 — the transition LoRA does the heavy lifting
ai-ksk profile
AI-KSK

Multi-image first/last-frame transitions in LTX 2.3 — the transition LoRA does the heavy lifting

#comfyui #ai #tutorial
Comments
4 min read
LTX 2.3 control was unusable — then a second upscale pass fixed it
ai-ksk profile
AI-KSK

LTX 2.3 control was unusable — then a second upscale pass fixed it

#comfyui #ai #tutorial
Comments
4 min read
LTX 2.3 R2V repaint, Qwen 2511 character swap, and a pseudo-swap that still lip-syncs
ai-ksk profile
AI-KSK

LTX 2.3 R2V repaint, Qwen 2511 character swap, and a pseudo-swap that still lip-syncs

#comfyui #ai #tutorial
Comments
5 min read
Abliterated Gemma 4 and GPT-OSS 120B on Ollama: how GPU offload layers decide what fits
ai-ksk profile
AI-KSK

Abliterated Gemma 4 and GPT-OSS 120B on Ollama: how GPU offload layers decide what fits

#comfyui #ai #tutorial
Comments
3 min read
Anima Preview 3 in ComfyUI: four graphs, one prompt system, and where the model actually breaks
ai-ksk profile
AI-KSK

Anima Preview 3 in ComfyUI: four graphs, one prompt system, and where the model actually breaks

#comfyui #ai #tutorial
Comments
4 min read
JoyAI-Image-Edit vs Qwen 2511: Progressive Editing Is the Real Gap
ai-ksk profile
AI-KSK

JoyAI-Image-Edit vs Qwen 2511: Progressive Editing Is the Real Gap

#comfyui #ai #tutorial
Comments
3 min read
VBVR for LTX 2.3: A Reasoning LoRA That Makes the Prompt Actually Happen
ai-ksk profile
AI-KSK

VBVR for LTX 2.3: A Reasoning LoRA That Makes the Prompt Actually Happen

#comfyui #ai #tutorial
Comments
3 min read
ERNIE-Image 8B: Posters and Chinese Text First, Portraits Second
ai-ksk profile
AI-KSK

ERNIE-Image 8B: Posters and Chinese Text First, Portraits Second

#comfyui #ai #tutorial
Comments
2 min read
LTX 2.3 Distill 1.1 Quietly Lands: Better Digital Humans, Better Image-to-Video
ai-ksk profile
AI-KSK

LTX 2.3 Distill 1.1 Quietly Lands: Better Digital Humans, Better Image-to-Video

#comfyui #ai #tutorial
Comments
3 min read
VoxCPM2 Voice Cloning: Twenty Minutes of Audio to a LoRA, in Two Actions
ai-ksk profile
AI-KSK

VoxCPM2 Voice Cloning: Twenty Minutes of Audio to a LoRA, in Two Actions

#comfyui #ai #tutorial
Comments
2 min read
WAI-ANIMA on Preview 3: Latent Upscale Beats Pixel Upscale, and 4M Pixels Is the Sweet Spot
ai-ksk profile
AI-KSK

WAI-ANIMA on Preview 3: Latent Upscale Beats Pixel Upscale, and 4M Pixels Is the Sweet Spot

#comfyui #ai #tutorial
Comments
3 min read
An Agent Inside the Canvas: Script to Assets to Storyboard to Video in One Flow
ai-ksk profile
AI-KSK

An Agent Inside the Canvas: Script to Assets to Storyboard to Video in One Flow

#comfyui #ai #tutorial
Comments
2 min read
GPT Image 2 Field Notes: What It Replaces Is Not the Drawing Step
ai-ksk profile
AI-KSK

GPT Image 2 Field Notes: What It Replaces Is Not the Drawing Step

#comfyui #ai #tutorial
Comments
2 min read
LTX 2.3 with VBVR 240K and Three-Tier Rendering: Three Optimal Graphs
ai-ksk profile
AI-KSK

LTX 2.3 with VBVR 240K and Three-Tier Rendering: Three Optimal Graphs

#comfyui #ai #tutorial
Comments
3 min read
One Graph for I2V, T2V, V2V and Audio-Driven Video at 8 Steps
ai-ksk profile
AI-KSK

One Graph for I2V, T2V, V2V and Audio-Driven Video at 8 Steps

#comfyui #ai #tutorial
Comments
2 min read
Two-Person Dialogue That Holds: Dual-Character LoRA Plus Prompt Relay, and a Subtitle Fixer
ai-ksk profile
AI-KSK

Two-Person Dialogue That Holds: Dual-Character LoRA Plus Prompt Relay, and a Subtitle Fixer

#comfyui #ai #tutorial
Comments
3 min read
Flux2 Klein Was Underrated: One Enhancement Node Turns Random Generation into Controlled Editing
ai-ksk profile
AI-KSK

Flux2 Klein Was Underrated: One Enhancement Node Turns Random Generation into Controlled Editing

#comfyui #ai #tutorial
Comments
3 min read
Repaint Instead of Cover: LTX 2.3 Text-Pollution Removal 1.0 with a Reference Frame
ai-ksk profile
AI-KSK

Repaint Instead of Cover: LTX 2.3 Text-Pollution Removal 1.0 with a Reference Frame

#comfyui #ai #tutorial
Comments
3 min read
LTX 2.3 Production Suite 2.0: Prompt Relay Plus Three-Tier Rendering, Five Graphs
ai-ksk profile
AI-KSK

LTX 2.3 Production Suite 2.0: Prompt Relay Plus Three-Tier Rendering, Five Graphs

#comfyui #ai #tutorial
Comments
4 min read
Sulphur 2 and 10Eros: Two LTX 2.3 Branches for Looser, Freer Video
ai-ksk profile
AI-KSK

Sulphur 2 and 10Eros: Two LTX 2.3 Branches for Looser, Freer Video

#comfyui #ai #tutorial
Comments
3 min read
Anima UltraReal: Turn Anime Characters into Real Photographs, Then Accelerate to 8 Steps
ai-ksk profile
AI-KSK

Anima UltraReal: Turn Anime Characters into Real Photographs, Then Accelerate to 8 Steps

#comfyui #ai #tutorial
Comments
3 min read
Multi-Image Reference for LTX 2.3: Separate Background, Character and Prop
ai-ksk profile
AI-KSK

Multi-Image Reference for LTX 2.3: Separate Background, Character and Prop

#comfyui #ai #tutorial
Comments
3 min read
Two Rescue Workflows: Erase Watermarks and Subtitle Garbage, Then Outpaint to Cinema Ratio
ai-ksk profile
AI-KSK

Two Rescue Workflows: Erase Watermarks and Subtitle Garbage, Then Outpaint to Cinema Ratio

#comfyui #ai #tutorial
Comments
3 min read
LTX 2.3 LipDub: Rewrite What a Person Says Without TTS or Voice Cloning
ai-ksk profile
AI-KSK

LTX 2.3 LipDub: Rewrite What a Person Says Without TTS or Voice Cloning

#comfyui #ai #tutorial
Comments
2 min read
LTX 2.3 Production Suite 2.5: IC Edit Strips Subtitles Between Render Tiers
ai-ksk profile
AI-KSK

LTX 2.3 Production Suite 2.5: IC Edit Strips Subtitles Between Render Tiers

#comfyui #ai #tutorial
Comments
4 min read
Anima Base 1.0: Text, Image, Tiled Upscale and Inpaint Workflows With LLLite Control
ai-ksk profile
AI-KSK

Anima Base 1.0: Text, Image, Tiled Upscale and Inpaint Workflows With LLLite Control

#comfyui #ai #tutorial
Comments
3 min read
LTX2.3 Long-Form MV: A For-Loop That Turns Six Images and One Song Into a Minute of Video
ai-ksk profile
AI-KSK

LTX2.3 Long-Form MV: A For-Loop That Turns Six Images and One Song Into a Minute of Video

#comfyui #ai #tutorial
Comments
3 min read
LTX Director Node: One Timeline Instead of Five Separate LTX2.3 Workflows
ai-ksk profile
AI-KSK

LTX Director Node: One Timeline Instead of Five Separate LTX2.3 Workflows

#comfyui #ai #tutorial
Comments
3 min read
Anima LoRA Batch Factory: ComfyUI Front-End, sd-scripts Training, Gemma 3 Auto-Tagging
ai-ksk profile
AI-KSK

Anima LoRA Batch Factory: ComfyUI Front-End, sd-scripts Training, Gemma 3 Auto-Tagging

#comfyui #ai #tutorial
Comments
2 min read
loading...