mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2025-04-20 03:13:30 +00:00
af02393c2a
By default, when applying a mask to a condition, the entire image will still be used for sampling. The new "set_area_to_bounds" option on the node will allow the user to automatically limit conditioning to the bounds of the mask. I've also removed the dependency on torchvision for calculating bounding boxes. I've taken the opportunity to fix some frustrating details in the other version: 1. An all-0 mask will no longer cause an error 2. Indices are returned as integers instead of floats so they can be used to index into tensors. |
||
|---|---|---|
| .. | ||
| cldm | ||
| extra_samplers | ||
| k_diffusion | ||
| ldm | ||
| sd1_tokenizer | ||
| t2i_adapter | ||
| cli_args.py | ||
| clip_vision_config_h.json | ||
| clip_vision_config_vitl.json | ||
| clip_vision.py | ||
| diffusers_convert.py | ||
| gligen.py | ||
| model_management.py | ||
| sample.py | ||
| samplers.py | ||
| sd1_clip_config.json | ||
| sd1_clip.py | ||
| sd2_clip_config.json | ||
| sd2_clip.py | ||
| sd.py | ||
| utils.py | ||