Lore
Single start-frame generation (cloud or local)
Create one styled first frame from the outline or depth image. It serves as the style reference for the video render. See single-vs-multi-reference-style-guidance.
Options
- Cloud: ChatGPT or Nano Banana.
- Local: the Z Image Turbo + control net workflow in ComfyUI.
Local protocol
- Drag the workflow into ComfyUI.
- Install missing custom nodes via Manager.
- Download and load the models.
- Drop in the first-frame control image, or load a video and take only its first frame.
- Write a simple prompt.
- Set control-net strength as low as possible, following the freedom principle in Control-pass choice as a freedom dial (outline vs depth vs blend).
- Run. Change the seed to explore variations.
The resulting image becomes the reference in free-ai-renderer-comfyui-workflow.