restyle

Installation
SKILL.md

restyle

Run every graph with the bundled client: python scripts/comfy_client.py --url $COMFY_URL run workflows/<file> --set NODE.INPUT=VALUE --out out/. Upload input files first with python scripts/comfy_client.py upload <file>. Before the first run on a server, check it with python scripts/preflight.py --url $COMFY_URL workflows/<file>. Node packs, model files, VRAM and weight licenses for this skill are in references/requirements.md. Use open-weights models only, and never swap in a hosted or closed model. LTX weights are under the Lightricks LTX license, which is not an OSI-approved open-source license (it is open weights with use conditions), so read it before commercial use.

Need Workflow Set
Keep the motion and change the look (depth-controlled IC-LoRA, with a Qwen-edited first frame) ltx_ic_lora_depth_restyle.api.json src.video, pos.text (look), e_pos.prompt (first-frame redraw), lat.length
Drive a photo with a reference clip's motion ltx25_motion_guide.api.json 199.file motion clip, 200.image photo, 950.file mask, 1002.image end key

Notes

  • Use 24 GB+ of VRAM. On Google Colab use an A100.
  • Video inputs go through upload too (the same endpoint takes any file).
  • The restyle graph needs ComfyUI-VideoHelperSuite and comfyui_controlnet_aux (see requirements). AudioAmplify in the motion-guide graph comes from a pack that is unverified: run preflight.
Installs
74
GitHub Stars
49
First Seen
Nov 1, 2026