Loop ForgeCurly hair in the rain
Works, from LTX 2.5 Creative Lab LoRAs, tested locally
- LoRA
- Alpha Gen at 1.0
- Output
- 1536×864, 121 frames at 24fps
- Sampling
- 8 steps, euler_ancestral
- Seed
- 1234
- Generated in
- 10 min
- Peak VRAM
- 10.8 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
The matte keeps single strands of curly hair against a busy neon street. I composited her over a forest creek, and a few strands keep the pink of the neon they were lit by. That pink is in the source footage, not in the matte.
Alpha Gen runs with an empty prompt. The source clip is the only guide.
Notes
The output is a grayscale matte, white for the subject. The composite multiplies the source by the matte and the background by its inverse, and was made after generation.
Run it yourself
Download everything for this test (.zip, 6.2 MB). It holds the workflow, every input it loads and a README. Copy the inputs into ComfyUI/input, put the models below in place and drag the workflow onto ComfyUI.
| File | Put it in | Size |
|---|---|---|
| ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors gated | models/diffusion_models | 21.5 GB |
| gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors gated | models/text_encoders | 15.4 GB |
| ltx-2.5-video-vae-bf16.safetensors gated | models/vae | 1.5 GB |
| ltx-2.5-audio-vae-bf16.safetensors gated | models/vae | 364.9 MB |
| ltx-2.5-22b-ic-lora-alpha-gen-0.9.safetensors gated | models/loras | 1.3 GB |
The Lightricks repositories (the LTX 2.5 base model and the LoRAs) are gated. Log in to Hugging Face and accept the terms on each repository page before downloading.
Custom nodes: ComfyUI-LTXVideo at commit 3bf3ca6. Everything else is part of ComfyUI 0.37.0 (commit 0f74f7fb, frontend 1.53.6).