2526 Commits (ce37c11164ebc452592f3b0e67fb63c8c16374c0)
 

Author SHA1 Message Date
comfyanonymous e2382b6adb Make lowvram less aggressive when there are large amounts of free memory. 7 months ago
comfyanonymous c24f897352 Fix to get fp8 working on T5 base. 7 months ago
comfyanonymous a5991a7aa6 Fix hunyuan dit text encoder weights always being in fp32. 7 months ago
comfyanonymous 2c038ccef0 Lower CLIP memory usage by a bit. 7 months ago
comfyanonymous b85216a3c0 Lower T5 memory usage by a few hundred MB. 7 months ago
comfyanonymous 82cae45d44 Fix potential issue with non clip text embeddings. 7 months ago
comfyanonymous 25853d0be8 Use common function for casting weights to input. 7 months ago
comfyanonymous 79040635da Remove unnecessary code. 7 months ago
comfyanonymous 66d35c07ce Improve artifacts on hydit, auraflow and SD3 on specific resolutions.
This breaks seeds for resolutions that are not a multiple of 16 in pixel
resolution by using circular padding instead of reflection padding but
should lower the amount of artifacts when doing img2img at those
resolutions.
7 months ago
comfyanonymous c75b50607b Less confusing exception if pillow() function fails. 7 months ago
comfyanonymous 4ba7fa0244 Refactor: Move sd2_clip.py to text_encoders folder. 7 months ago
bymyself ab76abc767
Active workflow use primary fg color (#4090) 7 months ago
Silver 9300058026
Add dpmpp_2s_ancestral as custom sampler (#4101)
Adding dpmpp_2s_ancestral as custom sampler node to enable its use with eta and s_noise when using custom sampling.
7 months ago
comfyanonymous f82d09c9b4 Update packaging workflow. 7 months ago
comfyanonymous e6829e7ac5 Add a way to set custom dependencies in the release workflow. 7 months ago
comfyanonymous 07f6a1a685 Handle case in the updater when master branch is not in local repo. 7 months ago
comfyanonymous e746965c50 Update nightly package workflow. 7 months ago
comfyanonymous 45a2842d7f Set stable releases as a prerelease initially.
This should give time to test the standalone package before making it live.
7 months ago
Robin Huang 17b41f622e
Change windows standalone URL to stable release. (#4065) 7 months ago
comfyanonymous cf4418b806 Don't treat Bert model like CLIP.
Bert can accept up to 512 tokens so any prompt with more than 77 should
just be passed to it as is instead of splitting it up like CLIP.
7 months ago
comfyanonymous 6225a7827c Add CLIPTextEncodeHunyuanDiT.
Useful for testing what each text encoder does.
7 months ago
filtered b6779d8df3
Fix undo incorrectly undoing text input (#4114)
Fixes an issue where under certain conditions, the ComfyUI custom undo / redo functions would not run when intended to.

When trying to undo an action like deleting several nodes, instead the native browser undo runs - e.g. a textarea gets focus and the last typed text is undone.  Clicking outside the text area and typing again just keeps doing the same thing.
7 months ago
comfyanonymous 8328a2d8cd Let hunyuan dit work with all prompt lengths. 7 months ago
comfyanonymous afe732bef9 Hunyuan dit can now accept longer prompts. 7 months ago
comfyanonymous a9ac56fc0d Own BertModel implementation that works with lowvram. 7 months ago
comfyanonymous 25b51b1a8b Hunyuan DiT lora support. 7 months ago
comfyanonymous 61a2b00bc2 Add HunyuanDiT support to readme. 7 months ago
comfyanonymous a5f4292f9f
Basic hunyuan dit implementation. (#4102)
* Let tokenizers return weights to be stored in the saved checkpoint.

* Basic hunyuan dit implementation.

* Fix some resolutions not working.

* Support hydit checkpoint save.

* Init with right dtype.

* Switch to optimized attention in pooler.

* Fix black images on hunyuan dit.
7 months ago
comfyanonymous f87810cd3e Let tokenizers return weights to be stored in the saved checkpoint. 7 months ago
comfyanonymous 10c919f4c7 Make it possible to load tokenizer data from checkpoints. 7 months ago
comfyanonymous ce80e69fb8 Avoid loading the dll when it's not necessary. 7 months ago
comfyanonymous 19944ad252 Add code to fix issues with new pytorch version on the standalone. 7 months ago
comfyanonymous 10b43ceea5 Remove duplicate code. 7 months ago
comfyanonymous 0a4c49c57c Support MT5. 7 months ago
comfyanonymous 88ed893034 Allow SPieceTokenizer to load model from a byte string. 7 months ago
comfyanonymous 334ba48cea More generic unet prefix detection code. 7 months ago
comfyanonymous 14764aa2e2 Rename LLAMATokenizer to SPieceTokenizer. 7 months ago
comfyanonymous b2c995f623 "auto" type is only relevant to the SetUnionControlNetType node. 7 months ago
Chenlei Hu 4151fbfa8a
Add error message on union controlnet (#4081) 7 months ago
Chenlei Hu 6045ed31f8
Supress frontend exception on unhandled message type (#4078)
* Supress frontend exception on unhandled message type

* nit
7 months ago
comfyanonymous f836e69346 Fix bug with SaveAudio node with --gpu-only 7 months ago
Chenlei Hu 5b69cfe7c3
Add timestamp to execution messages (#4076)
* Add timestamp to execution messages

* Add execution_end message

* Rename to execution_success
7 months ago
comfyanonymous 95fa9545f1 Only append zero to noise schedule if last sigma isn't zero. 7 months ago
Greg Wainer 11b74147ee
Fix/webp exif little endian (#4061)
* Fix for isLittleEndian flag in parseExifData.

* Add break after reading first exif chunk in getWebpMetadata.
7 months ago
comfyanonymous 6ab8cad22e Implement beta sampling scheduler.
It is based on: https://arxiv.org/abs/2407.12173

Add "beta" to the list of schedulers and the BetaSamplingScheduler node.
7 months ago
bymyself 011b11d8d7
LoadAudio restores file value from workflow (#4043)
* LoadAudio restores file value from workflow

* use onAfterGraphConfigured

* Don't use anonnymous function
7 months ago
comfyanonymous ff6ca2a892 Move PAG to model_patches/unet section.
Move other unet model_patches nodes to model_patches/unet section.
7 months ago
bymyself 374e093e09
Disable audio widget trying to get previews (#4044) 7 months ago
喵哩个咪 855789403b
support clip-vit-large-patch14-336 (#4042)
* support clip-vit-large-patch14-336

* support clip-vit-large-patch14-336
7 months ago
comfyanonymous 6f7869f365 Get clip vision image size from config. 7 months ago