1167 Commits (6fb084f39de495ca2cdfd482720069378d6e68ae)
 

Author SHA1 Message Date
comfyanonymous 6fb084f39d Reduce floating point rounding errors in loras. 2 years ago
comfyanonymous 91ed2815d5 Add a node to merge CLIP models. 2 years ago
comfyanonymous 907c9fbf0d Refactor to make it easier to set the api path. 2 years ago
comfyanonymous 30ea187160 Merge branch 'use-relative-paths' of https://github.com/mcmonkey4eva/ComfyUI 2 years ago
comfyanonymous eed3042830 Move conditioning concat node to conditioning section. 2 years ago
comfyanonymous 8a577966c5 Enables a way to save workflows in api format in frontend.
Enable the dev mode in the settings to see it.
2 years ago
comfyanonymous bdba394290 Add a canny preprocessor node. 2 years ago
comfyanonymous 6f914fb77d Print prestartup times for custom nodes. 2 years ago
comfyanonymous 3bc8be33e4 Don't let custom nodes overwrite base nodes. 2 years ago
comfyanonymous 876dadca84 Highlight nodes with errors in red even when workflow works fine. 2 years ago
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
Alex "mcmonkey" Goodwin 5797ff89b0 use relative paths for all web connections
This enables local reverse-proxies to host ComfyUI on a path, eg "http://example.com/ComfyUI/" in such a way that at least everything I tested works. Without this patch, proxying ComfyUI in this way will yield errors.
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