Lore

Free AI renderer ComfyUI workflow: setup and single-reference run

The main free, open-source workflow. It takes control-pass videos, a reference image and a prompt, and generates the rendered video locally. It is built on Inner Reflections' Skyreels + VACE merged model and implements Generative AI rendering with control nets, reference image and prompt.

Setup

  1. Drag the workflow into ComfyUI.
  2. Install missing custom nodes in Manager and restart.
  3. Download the models using the links in the notes beside the loaders.

Run

  1. Set the resolution. The lizard demo used square.
  2. Do not skip frames.
  3. Load the outline pass, and depth too if wanted (Control-pass choice as a freedom dial (outline vs depth vs blend)).
  4. Add the reference image (Single start-frame vs multiple references for style guidance) and a prompt.
  5. Run. To explore, change the seed or the prompt.

Access

Everything is free and open source and runs on your own computer. RunPod templates are an option for people without a powerful GPU. Patreon supporters fund the work and get the advanced workflows and example files.

Limits

The base workflow is limited in shot length (ai-render-shot-length-limit-and-batch-chaining). Control passes can come from Free AI preparation workflow (outline and depth from a viewport render) or from the Blender passes.