-
-
Notifications
You must be signed in to change notification settings - Fork 10
ControlNet and Style Transfer
A full ControlNet panel ships in the generation UI. Two ways to use it:
- Preset mode - a grid of presets (Canny, Depth, OpenPose, LineArt, Scribble, Soft Edge, and more), filtered to what suits the active model family. In preset mode your reference image is preprocessed (for example edge detection) before being used as guidance.
- Custom mode - pick the ControlNet model and preprocessor manually.
Capabilities:
- Reference image via upload, paste, or drag-and-drop.
- Preprocessor preview so you can see the control map before generating.
- Strength slider plus start% / end% timing sliders.
- Auto-setup: missing ControlNet models are downloaded automatically, the
comfyui_controlnet_auxpreprocessor pack is cloned from GitHub, ComfyUI is restarted, and the install is verified. ControlNet setup failures do not block core generation.
Anima-based checkpoints are Wan2.1 DiT models, not classic UNets, so standard ControlNet cannot be applied to them. When an Anima model is active, ControlNet automatically routes through the Anima LLLite path (the ComfyUI-Anima-LLLite node), which has its own one-click install flow if the extension is missing.
This routing depends on the model being detected as the Anima family. Detection works even for Anima fine-tunes that were renamed without an anima or yume token in the filename (for example PerfectDeliberate): MooshieUI inspects the safetensors tensor structure, recognizes the Wan2.1 transformer blocks, and treats the checkpoint as Anima. If a model is still misdetected, you can set its family manually with the family override in the model picker.
Style Transfer is a separate feature from ControlNet. It uses RFInversion (via the ComfyUI-Untwisting-RoPE node) together with an advanced image-scaling node to transfer the look of a reference image.
- Reference image via upload, paste, or drag-and-drop.
- MooshieUI checks that the required nodes are available.
- It warns you if you have selected an ancestral sampler, which is not compatible with this technique.
Getting started
Prompting
Generation features
Models and output
Deployment
Help