workflows/ (or a small graph built in code) through ComfyUI’s /prompt. You only need the models for the features you use. The model picker in the generator shows which image and video models are installed.
Folders below are relative to ComfyUI/models/.
Image generation and editing
The default image model. It powers generation, quick edit, edit text, expand, inpaint, style transfer, comment edits and creative upscale.Other image models (optional)
Qwen Image 2512 is loaded with the ComfyArt Precise UNET Loader node. ComfyUI’s
--fast fp8_matrix_mult turns unscaled fp8 checkpoints like this one into noise; the loader skips that path for the model it loads. Ideogram 4 expects a structured caption, which the default Agent writes for you.Image tools
Video
Animate image, video generation and video extend use MiniMax H3:
Video trim and the video editor use core nodes only.
Speech and text recognition
gemma4_e4b_it_fp8_scaled.safetensors in text_encoders powers voice input and, by default, text recognition for Edit Text and Extract Text. Text recognition can use the Agent instead; see Agent settings.
Reference modes
Line art, depth, pose and the other structure modes use the comfyui_controlnet_aux preprocessors. MLSD, HED, normal and segmentation download their annotator weights on first use. With Qwen Image 2512, structure modes also useQwen-Image-2512-Fun-Controlnet-Union-2602.safetensors in controlnet.