1094 Commits (50abf7c938f5787530264a383d2b8d1887768a05)
 

Author SHA1 Message Date
comfyanonymous 50abf7c938 Merge branch 'patch-1' of https://github.com/jjangga0214/ComfyUI 2 years ago
comfyanonymous 8248babd44 Use pytorch attention by default on nvidia when xformers isn't present.
Add a new argument --use-quad-cross-attention
2 years ago
comfyanonymous 9b93b920be Add CheckpointSave node to save checkpoints.
The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.

Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32

Anything that patches the model weights like merging or loras will be
saved.

The output directory is currently set to: output/checkpoints but that might
change in the future.
2 years ago
comfyanonymous b72a7a835a Support loras based on the stability unet implementation. 2 years ago
comfyanonymous c71a7e6b20 Fix ddim + inpainting not working. 2 years ago
jjangga0214 530e408ab8
docs(extra model paths): add LyCORIS path 2 years ago
comfyanonymous 4eab00e14b Set the seed in the SDE samplers to make them more reproducible. 2 years ago
comfyanonymous cef6aa62b2 Add support for TAESD decoder for SDXL. 2 years ago
comfyanonymous 20f579d91d Add DualClipLoader to load clip models for SDXL.
Update LoadClip to load clip models for SDXL refiner.
2 years ago
comfyanonymous b7933960bb Fix CLIPLoader node. 2 years ago
comfyanonymous 78d8035f73 Fix bug with controlnet. 2 years ago
Dr.Lt.Data c9f5d5b2e1
optimize: support preview mode for mask editor. (#755)
* support preview mode for mask editor.
* use original file reference instead of loaded frontend blob

bugfix:
* prevent file open dialog when save to load image

* bugfix: cannot clear previous mask painted image's alpha

* bugfix

* bugfix

---------

Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
2 years ago
comfyanonymous 05676942b7 Add some more transformer hooks and move tomesd to comfy_extras.
Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.
2 years ago
comfyanonymous fa28d7334b Remove useless code. 2 years ago
comfyanonymous 8607c2d42d Move latent scale factor from VAE to model. 2 years ago
comfyanonymous 30a3861946 Fix bug when yaml config has no clip params. 2 years ago
comfyanonymous 9e37f4c7d5 Fix error with ClipVision loader node. 2 years ago
comfyanonymous 3e0686ce94 Add SDXL support to readme and improve the Running section. 2 years ago
comfyanonymous 7573897a3e Merge branch 'master' of https://github.com/VladislavNekto/ComfyUI 2 years ago
comfyanonymous 9f83b098c9 Don't merge weights when shapes don't match and print a warning. 2 years ago
comfyanonymous f87ec10a97 Support base SDXL and SDXL refiner models.
Large refactor of the model detection and loading code.
2 years ago
Vladislav ca485d2328
Update README.md
Information about running at RX7600
2 years ago
comfyanonymous 9fccf4aa03 Add original_shape parameter to transformer patch extra_options. 2 years ago
comfyanonymous 852cf4db99 Merge branch 'widget-input-overlapping' of https://github.com/ssitu/ComfyUI 2 years ago
comfyanonymous 6f0f8aa7aa Merge branch 'reroute-disconnect-fix' of https://github.com/ssitu/ComfyUI 2 years ago
comfyanonymous 51581dbfa9 Fix last commits causing an issue with the text encoder lora. 2 years ago
comfyanonymous bf3f271775 Add some nodes for basic model merging. 2 years ago
comfyanonymous 8125b51a62 Keep a set of model_keys for faster add_patches. 2 years ago
comfyanonymous 45beebd33c Add a type of model patch useful for model merging. 2 years ago
ssit 6f54b01954 Fix reroute node connecting different types 2 years ago
ssit 8c3d24434a Fix overlapping when converting widgets to inputs 2 years ago
comfyanonymous 186f92042b Merge branch 'improve-keyboard' of https://github.com/reaper47/ComfyUI 2 years ago
reaper47 96e8307bd3 Clean keybinds extension 2 years ago
comfyanonymous 036a22077c Fix k_diffusion math being off by a tiny bit during txt2img. 2 years ago
comfyanonymous 8883cb0f67 Add a way to set patches that modify the attn2 output.
Change the transformer patches function format to be more future proof.
2 years ago
comfyanonymous cd930d4e7f pop clip vision keys after loading them. 2 years ago
comfyanonymous c9e4a8c9e5 Not needed anymore. 2 years ago
comfyanonymous fb4bf7f591 This is not needed anymore and causes issues with alphas_cumprod. 2 years ago
comfyanonymous 45be2e92c1 Fix DDIM v-prediction. 2 years ago
comfyanonymous e619278730 Merge branch 'html5-dialog' of https://github.com/reaper47/ComfyUI 2 years ago
comfyanonymous 8c9c94b5f3 Add bicubic upscale method. 2 years ago
comfyanonymous e6e50ab2dd Fix an issue when alphas_comprod are half floats. 2 years ago
comfyanonymous ae43f09ef7 All the unet weights should now be initialized with the right dtype. 2 years ago
comfyanonymous cf3974c829 Update readme with command to install pytorch with ROCm5.5.
Remove mentions of python 3.10 since 3.11 works fine now.
2 years ago
comfyanonymous f7edcfd927 Add a --gpu-only argument to keep and run everything on the GPU.
Make the CLIP model work on the GPU.
2 years ago
comfyanonymous 7bf89ba923 Initialize more unet weights as the right dtype. 2 years ago
comfyanonymous e21d9ad445 Initialize transformer unet block weights in right dtype at the start. 2 years ago
reaper47 3fbd0abc5f Add missed .comfy-table in CSS 2 years ago
reaper47 34ddbfdc8a Beautify settings dialog 2 years ago
comfyanonymous 6253ec4aef Fix server crashing because of terminated websocket connection. 2 years ago