KenSchae
/
ComfyUI
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
1156 Commits
1 Branch
1 Tag
56 MiB
Tree: b2f03164c7
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.
1 year ago
comfyanonymous 46dc050c9f Fix potential tensors being on different devices issues.
1 year ago
comfyanonymous 90aa597099 Add back roundRect to fix issue on firefox ESR.
1 year ago
comfyanonymous f4b9390623 Add a random string to the temp prefix for PreviewImage.
1 year ago
comfyanonymous 2b2a1474f7 Move to litegraph.
1 year ago
comfyanonymous cef30cc6b6 Merge branch 'hidpi-canvas' of https://github.com/EHfive/ComfyUI
1 year ago
comfyanonymous 880c9b928b Update litegraph to latest.
1 year ago
Huang-Huang Bao 05e6eac7b3
Scale graph canvas based on DPI factor
1 year ago
Dr.Lt.Data 99abcbef41
feat/startup-script: Feature to avoid package installation errors when installing custom nodes. (#856)
1 year ago
comfyanonymous 606a537090 Support SDXL embedding format with 2 CLIP.
1 year ago
comfyanonymous 6ad0a6d7e2 Don't patch weights when multiplier is zero.
1 year ago
comfyanonymous af15add967 Fix annoyance with textbox unselecting in chromium.
1 year ago
comfyanonymous d5323d16e0 latent2rgb matrix for SDXL.
1 year ago
comfyanonymous 0ae81c03bb Empty cache after model unloading for normal vram and lower.
1 year ago
comfyanonymous d3f5998218 Support loading clip_g from diffusers in CLIP Loader nodes.
1 year ago
comfyanonymous a9a4ba7574 Fix merging not working when model2 of model merge node was a merge.
1 year ago
comfyanonymous febea8c101 Merge branch 'bugfix/img-offset' of https://github.com/ltdrdata/ComfyUI
1 year ago
Dr.Lt.Data 9caab9380d
fix: Image.ANTIALIAS is no longer available. (#847)
1 year ago
Dr.Lt.Data d43cff2105 bugfix: image widget's was mis-aligned when node has multiline widget
1 year ago
comfyanonymous c2d407b0f7 Merge branch 'Yaruze66-patch-1' of https://github.com/Yaruze66/ComfyUI
1 year ago
comfyanonymous bb5fbd29e9 Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI
1 year ago
comfyanonymous 2c9d98f3e6 CLIPTextEncodeSDXL now works when prompts are of very different sizes.
1 year ago
comfyanonymous e7bee85df8 Add arguments to run the VAE in fp16 or bf16 for testing.
1 year ago
comfyanonymous f5232c4869 Fix 7z error when extracting package.
1 year ago
comfyanonymous 608fcc2591 Fix bug with weights when prompt is long.
1 year ago
comfyanonymous ddc6f12ad5 Disable autocast in unet for increased speed.
1 year ago
comfyanonymous 603f02d613 Fix loras not working when loading checkpoint with config.
1 year ago
comfyanonymous ccb1b25908 Add a conditioning concat node.
1 year ago
comfyanonymous af7a49916b Support loading unet files in diffusers format.
1 year ago
comfyanonymous e57cba4c61 Add gpu variations of the sde samplers that are less deterministic
1 year ago
comfyanonymous f81b192944 Add logit scale parameter so it's present when saving the checkpoint.
1 year ago
comfyanonymous acf95191ff Properly support SDXL diffusers loras for unet.
1 year ago
mara c61a95f9f7 Fix size check for conditioning mask
1 year ago
comfyanonymous 8d694cc450 Fix issue with OSX.
1 year ago
comfyanonymous c02f3baeaf Now the model merge blocks node will use the longest match.
1 year ago
comfyanonymous 3a09fac835 ConditioningAverage now also averages the pooled output.
1 year ago
comfyanonymous d94ddd8548 Add text encode nodes to control the extra parameters in SDXL.
1 year ago
comfyanonymous c3e96e637d Pass device to CLIP model.
1 year ago
comfyanonymous 5e6bc824aa Allow passing custom path to clip-g and clip-h.
1 year ago
comfyanonymous dc9d1f31c8 Improvements for OSX.
1 year ago
Yaruze66 9ae6ff65bc
Update extra_model_paths.yaml.example: add RealESRGAN path
1 year ago
comfyanonymous 103c487a89 Cleanup.
1 year ago
comfyanonymous ae948b42fa Add taesd weights to standalones.
1 year ago
comfyanonymous 2c4e0b49b7 Switch to fp16 on some cards when the model is too big.
1 year ago
comfyanonymous 6f3d9f52db Add a --force-fp16 argument to force fp16 for testing.
1 year ago
comfyanonymous 1c1b0e7299 --gpu-only now keeps the VAE on the device.
1 year ago
comfyanonymous ce35d8c659 Lower latency by batching some text encoder inputs.
1 year ago
comfyanonymous 3b6fe51c1d Leave text_encoder on the CPU when it can handle it.
1 year ago
comfyanonymous b6a60fa696 Try to keep text encoders loaded and patched to increase speed.
1 year ago
comfyanonymous 97ee230682 Make highvram and normalvram shift the text encoders to vram and back.
1 year ago