Grayscale market
Works, from LTX 2.5 Creative Lab LoRAs, tested locally



- LoRA
- Colorization at 1.0
- Output
- 1152×640, 121 frames at 24fps
- Sampling
- 8 steps, euler_ancestral
- Seed
- 42
- Generated in
- 10 min
- Peak VRAM
- 11.0 GiB
- Ran on
- RTX 3060, 12GB (local)
What was wired in
I took a generated market clip, turned it grayscale and gave that to the LoRA. The colours it picked for the fruit, the vegetables, the awning and the clothes came out close to the original.
Reference shows a market stall under a striped awning where a bearded vendor in an apron is arranging fruit in wooden crates while a customer in a headscarf reaches for lemons, with a busy market crowd behind, rendered in monochrome under soft daylight. Edited shows the same scene with natural colors restored. COLORIZE a green and white striped awning, bright orange oranges, red apples and yellow bananas in pale wooden crates, the vendor in a blue apron with a grey beard, the customer in a dark red headscarf and coat, warm natural skin tones and a muted colorful crowd behind. Subject identity, framing, and background geometry are identical to the reference; only color information differs between reference and edited.
Notes
The trigger is COLORIZE. The colours you name in the prompt are the colours you get.
Run it yourself
Download everything for this test (.zip, 3.8 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-colorization-0.9.safetensors gated | models/loras | 906.1 MB |
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).
