mlapointe
/
ComfyUI-Repo
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,156 Commits
1 Branch
0 Tags
13 MiB
main
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'b2f03164c7'
${ noResults }
Commit Graph

1156 Commits (b2f03164c727d2252ac8509361082ba88481cfb1)
 

Author SHA1 Message Date
comfyanonymous b2f03164c7 Prevent the clip_g position_ids key from being saved in the checkpoint. 
This is to make it match the official checkpoint.
 2 years ago
comfyanonymous 46dc050c9f Fix potential tensors being on different devices issues. 2 years ago
comfyanonymous 90aa597099 Add back roundRect to fix issue on firefox ESR. 2 years ago
comfyanonymous f4b9390623 Add a random string to the temp prefix for PreviewImage. 2 years ago
comfyanonymous 2b2a1474f7 Move to litegraph. 2 years ago
comfyanonymous cef30cc6b6 Merge branch 'hidpi-canvas' of https://github.com/EHfive/ComfyUI 2 years ago
comfyanonymous 880c9b928b Update litegraph to latest. 2 years ago
Huang-Huang Bao 05e6eac7b3
Scale graph canvas based on DPI factor 
Similar to fixes in litegraph.js editor demo:
3ef215cf11/editor/js/code.js (L19-L28)

Also workarounds to address viewpoint problem of lightgrapgh.js in DPI scaling scenario.

Fixes #161
 2 years ago
Dr.Lt.Data 99abcbef41
feat/startup-script: Feature to avoid package installation errors when installing custom nodes. (#856) 
* support startup script for installation without locking on windows

* modified: Instead of executing scripts from the startup-scripts directory, I will change it to execute the prestartup_script.py for each custom node.
 2 years ago
comfyanonymous 606a537090 Support SDXL embedding format with 2 CLIP. 2 years ago
comfyanonymous 6ad0a6d7e2 Don't patch weights when multiplier is zero. 2 years ago
comfyanonymous af15add967 Fix annoyance with textbox unselecting in chromium. 2 years ago
comfyanonymous d5323d16e0 latent2rgb matrix for SDXL. 2 years ago
comfyanonymous 0ae81c03bb Empty cache after model unloading for normal vram and lower. 2 years ago
comfyanonymous d3f5998218 Support loading clip_g from diffusers in CLIP Loader nodes. 2 years ago
comfyanonymous a9a4ba7574 Fix merging not working when model2 of model merge node was a merge. 2 years ago
comfyanonymous febea8c101 Merge branch 'bugfix/img-offset' of https://github.com/ltdrdata/ComfyUI 2 years ago
Dr.Lt.Data 9caab9380d
fix: Image.ANTIALIAS is no longer available. (#847) 
* modify deprecated api call

* prevent breaking old Pillow users

* change LANCZOS to BILINEAR
 2 years ago
Dr.Lt.Data d43cff2105 bugfix: image widget's was mis-aligned when node has multiline widget 2 years ago
comfyanonymous c2d407b0f7 Merge branch 'Yaruze66-patch-1' of https://github.com/Yaruze66/ComfyUI 2 years ago
comfyanonymous bb5fbd29e9 Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI 2 years ago
comfyanonymous 2c9d98f3e6 CLIPTextEncodeSDXL now works when prompts are of very different sizes. 2 years ago
comfyanonymous e7bee85df8 Add arguments to run the VAE in fp16 or bf16 for testing. 2 years ago
comfyanonymous f5232c4869 Fix 7z error when extracting package. 2 years ago
comfyanonymous 608fcc2591 Fix bug with weights when prompt is long. 2 years ago
comfyanonymous ddc6f12ad5 Disable autocast in unet for increased speed. 2 years ago
comfyanonymous 603f02d613 Fix loras not working when loading checkpoint with config. 2 years ago
comfyanonymous ccb1b25908 Add a conditioning concat node. 2 years ago
comfyanonymous af7a49916b Support loading unet files in diffusers format. 2 years ago
comfyanonymous e57cba4c61 Add gpu variations of the sde samplers that are less deterministic 
but faster.
 2 years ago
comfyanonymous f81b192944 Add logit scale parameter so it's present when saving the checkpoint. 2 years ago
comfyanonymous acf95191ff Properly support SDXL diffusers loras for unet. 2 years ago
mara c61a95f9f7 Fix size check for conditioning mask 
The wrong dimensions were being checked, [1] and [2] are the image size.
not [2] and [3]. This results in an out-of-bounds error if one of them
actually matches.
 2 years ago
comfyanonymous 8d694cc450 Fix issue with OSX. 2 years ago
comfyanonymous c02f3baeaf Now the model merge blocks node will use the longest match. 2 years ago
comfyanonymous 3a09fac835 ConditioningAverage now also averages the pooled output. 2 years ago
comfyanonymous d94ddd8548 Add text encode nodes to control the extra parameters in SDXL. 2 years ago
comfyanonymous c3e96e637d Pass device to CLIP model. 2 years ago
comfyanonymous 5e6bc824aa Allow passing custom path to clip-g and clip-h. 2 years ago
comfyanonymous dc9d1f31c8 Improvements for OSX. 2 years ago
Yaruze66 9ae6ff65bc
Update extra_model_paths.yaml.example: add RealESRGAN path 2 years ago
comfyanonymous 103c487a89 Cleanup. 2 years ago
comfyanonymous ae948b42fa Add taesd weights to standalones. 2 years ago
comfyanonymous 2c4e0b49b7 Switch to fp16 on some cards when the model is too big. 2 years ago
comfyanonymous 6f3d9f52db Add a --force-fp16 argument to force fp16 for testing. 2 years ago
comfyanonymous 1c1b0e7299 --gpu-only now keeps the VAE on the device. 2 years ago
comfyanonymous ce35d8c659 Lower latency by batching some text encoder inputs. 2 years ago
comfyanonymous 3b6fe51c1d Leave text_encoder on the CPU when it can handle it. 2 years ago
comfyanonymous b6a60fa696 Try to keep text encoders loaded and patched to increase speed. 
load_model_gpu() is now used with the text encoder models instead of just
the unet.
 2 years ago
comfyanonymous 97ee230682 Make highvram and normalvram shift the text encoders to vram and back. 
This is faster on big text encoder models than running it on the CPU.
 2 years ago