The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Commits on master
ReVision support: unclip nodes can now be used with SDXL.
39ac856 comfyanonymous committed 3 years ago
Add support for clip g vision model to CLIPVisionLoader.
76d53c4 comfyanonymous committed 3 years ago
Add node to scale image to a total amount of pixels keeping aspect.
fc99fa5 comfyanonymous committed 3 years ago
Merge branch 'add-user-css' of https://github.com/pythongosssss/ComfyUI
eb5c991 comfyanonymous committed 3 years ago
Fix issue with not freeing enough memory when sampling.
be9c5e2 comfyanonymous committed 3 years ago
Fix potential issues with patching models when saving checkpoints.
c28db1f comfyanonymous committed 3 years ago
Merge branch 'add-growmask-node' of https://github.com/coreyryanhanson/ComfyUI
1498f1a comfyanonymous committed 3 years ago
Add --disable-smart-memory for those that want the old behaviour.
3aee33b comfyanonymous committed 3 years ago
Support small diffusers controlnet so both types are now supported.
2c97c30 comfyanonymous committed 3 years ago
Add a "resize_source" option to Image and Latent CompositeMasked.
6dc02c7 comfyanonymous committed 3 years ago
Add bypass to readme and add a Bypass menu option to the nodes.
7567c4a comfyanonymous committed 3 years ago
Add option to use different xformers version in the github workflow.
d4380f3 comfyanonymous committed 3 years ago