DEV Community

AI-KSK
AI-KSK

Posted on Originally published at huggingface.co

LTX: ltx Image Controlnet — 4 Workflows, Read From the Graphs

LTX: ltx Image Controlnet — 4 Workflows, Read From the Graphs

This release ships 4 workflow files built around LTX. Together they total 233 nodes. Rather than summarise the video, this write-up reads the graphs directly — what each one loads, how big its latents are, and which sampler it runs.

The workflows at a glance

Workflow Nodes Links Sampler Latent
ltx 2对口型 83 88 euler, gradient_estimation 768x512 97f
Z Image Controlnet 2.1 2601 局部重绘 51 69 — —
Z Image Controlnet 2.1 2601 文生图 50 65 — —
Z Image 三种放大 49 74 — —

The node count range is wide: Z Image 三种放大 at 49 nodes against ltx 2对口型 at 83. That gap is usually the difference between a single-pass preview graph and one that adds conditioning, upscale stages, or a second sampling pass.

What the graphs load

Model file Loader node
ltx-2-19b-dev-fp8.safetensors LTXVAudioVAELoader
ltx-2-spatial-upscaler-x2-1.0.safetensors LatentUpscaleModelLoader
MelBandRoFormer_comfy/MelBandRoformer_fp16.safetensors MelBandRoFormerModelLoader
gemma_3_12B_it_fp8_e4m3fn.safetensors LTXAVTextEncoderLoader
qwen_3_4b.safetensors CLIPLoader
z_image_turbo_bf16.safetensors UNETLoader
ae.safetensors VAELoader
Z-Image-Turbo-Fun-Controlnet-Union-2.1-2601-8steps.safetensors ModelPatchLoader
ema_vae_fp16.safetensors SeedVR2LoadVAEModel
seedvr2_ema_7b-Q4_K_M.gguf SeedVR2LoadDiTModel
Z-Image-Turbo-Fun-Controlnet-Tile-2.1-2601-8steps.safetensors ModelPatchLoader
4x_NMKD-Siax_200k.pth UpscaleModelLoader

LoRAs in play

LoRA Weight
ltx-2-19b-distilled-lora-384.safetensors 1
ltx-2-19b-ic-lora-detailer.safetensors 0.6
ltx-2-19b-lora-camera-control-static.safetensors 1
lin9527.safetensors 0.6000000000000001

Not every LoRA runs at 1.0 — the non-default weights here are [0.6]. A weight above 1.0 amplifies the LoRA's effect past what its author trained for; below 1.0 backs it off. Both are deliberate tuning choices, not leftovers.

Latent geometry

Distinct latent configurations across the set: 768x512 97f.

The frame count matters more than the pixel dimensions here. A graph at 97 frames is built for roughly a four-second unit; one at 121 frames is closer to five. Sigma schedules do not transfer cleanly between them, so treat each geometry as its own tuning target.

Sampler choice

Samplers used: euler, gradient_estimation.

A plain euler is deterministic — good when the constraint is the point and noise per step would only perturb the trajectory. Ancestral variants inject noise each step and are the right pick when you want the model to explore rather than commit.

Where this set is weak

  1. Node count is not quality. The largest graph is not automatically the best one; a 40-node graph with a good prompt beats a 200-node graph with a bad one.
  2. No measured comparison in the files. The workflows carry settings, not benchmarks. Any quality claim needs your own A/B run.
  3. Model files are not included. You supply the weights; the graphs only reference filenames.
  4. Version drift. A graph pinned to a specific checkpoint revision will run on a newer one but may produce different output.

Practical order

Open the smallest graph first. It has the fewest moving parts and will confirm your models load before you spend time on the elaborate ones.

Workflows

4 graphs published on RunningHub with invite code rh-v1111:

  • ltx 2对口型
  • Z Image Controlnet 2.1 2601 局部重绘
  • Z Image Controlnet 2.1 2601 文生图
  • Z Image 三种放大

Files

https://huggingface.co/AI-KSK/ksk-video-159-comfyui-workflows

Video walkthrough: https://youtu.be/LH1FquAz5O8
Bilibili: https://www.bilibili.com/video/BV1LLkFBhEgm/

Notes

  • Workflow files only. Model weights are not included and each keeps its own licence.
  • Node counts, geometries and loader filenames above are read from the published JSON files.
  • Independent AI-KSK release. Not affiliated with the model authors or RunningHub.

Optional API platform - 88API (affiliate link)

Explore 88API for access to multiple AI model APIs. Available models, routes and prices are listed on the platform; Alipay top-ups are supported.

https://88api.ai/sign-up?aff=usx3

Disclosure: I may earn a commission from eligible purchases after you register through this referral link.

Top comments (0)