Add Github Workflow for releasing stable versions and standalone bundle. #3949
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
huchenlei
reviewed
Jul 5, 2024
| with: | ||
| fetch-depth: 0 | ||
| persist-credentials: false | ||
| - shell: bash |
There was a problem hiding this comment.
Just curious, how are we expected to test this command/workflow? Is there an easy way to run this long command locally?
There was a problem hiding this comment.
The best way is to run it in Comfy-Mirror repo.
https://github.com/Comfy-Org/ComfyUI-Mirror/actions/workflows/release.yml
Are you talking about a command specifically? Or the entire github workflow?
csokun
pushed a commit
to csokun/ComfyUI
that referenced
this pull request
Jul 13, 2024
…le. (comfyanonymous#3949) * Add stable release. * Only build CUDA 12.1 + 3.11 Python. * Upgrade checkout and setup-python to latest version. * lzma2 * Update artifact name to be ComfyUI_windows_portable_nvidia.7z
pmason314
pushed a commit
to pmason314/ComfyUI
that referenced
this pull request
Jul 26, 2024
…le. (comfyanonymous#3949) * Add stable release. * Only build CUDA 12.1 + 3.11 Python. * Upgrade checkout and setup-python to latest version. * lzma2 * Update artifact name to be ComfyUI_windows_portable_nvidia.7z
chenbaiyujason
added a commit
to NeoWorldTeam/ComfyUI
that referenced
this pull request
Aug 6, 2024
commit de17a97 Author: comfyanonymous <[email protected]> Date: Tue Aug 6 03:30:28 2024 -0400 Unload all models if there's an OOM error. commit c14ac98 Author: comfyanonymous <[email protected]> Date: Tue Aug 6 03:22:39 2024 -0400 Unload models and load them back in lowvram mode no free vram. commit 2894511 Author: Robin Huang <[email protected]> Date: Mon Aug 5 22:46:09 2024 -0700 Clone taesd with depth of 1 to reduce download size. (comfyanonymous#4232) commit f3bc402 Author: Silver <[email protected]> Date: Tue Aug 6 07:45:24 2024 +0200 Add format metadata to CLIP save to make compatible with diffusers safetensors loading (comfyanonymous#4233) commit 841e74a Author: Chenlei Hu <[email protected]> Date: Tue Aug 6 01:27:28 2024 -0400 Change browser test CI python to 3.8 (comfyanonymous#4234) commit 2d75df4 Author: comfyanonymous <[email protected]> Date: Mon Aug 5 21:58:28 2024 -0400 Flux tweak memory usage. commit 1abc9c8 Author: Robin Huang <[email protected]> Date: Mon Aug 5 17:07:16 2024 -0700 Stable release uses cached dependencies (comfyanonymous#4231) * Release stable based on existing tag. * Update default cuda to 12.1. commit 8edbcf5 Author: comfyanonymous <[email protected]> Date: Mon Aug 5 16:24:04 2024 -0400 Improve performance on some lowend GPUs. commit e545a63 Author: comfyanonymous <[email protected]> Date: Mon Aug 5 12:31:12 2024 -0400 This probably doesn't work anymore. commit 33e5203 Author: bymyself <[email protected]> Date: Mon Aug 5 09:25:28 2024 -0700 Don't cache index.html (comfyanonymous#4211) commit a178e25 Author: a-One-Fan <[email protected]> Date: Mon Aug 5 08:26:20 2024 +0300 Fix Flux FP64 math on XPU (comfyanonymous#4210) commit 78e133d Author: comfyanonymous <[email protected]> Date: Sun Aug 4 21:59:42 2024 -0400 Support simple diffusers Flux loras. commit 7afa985 Author: Silver <[email protected]> Date: Sun Aug 4 23:10:02 2024 +0200 Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' (comfyanonymous#4200) commit ddb6a9f Author: comfyanonymous <[email protected]> Date: Sun Aug 4 15:59:02 2024 -0400 Set the step in EmptySD3LatentImage to 16. These models work better when the res is a multiple of 16. commit 3b71f84 Author: comfyanonymous <[email protected]> Date: Sun Aug 4 15:45:43 2024 -0400 ONNX tracing fixes. commit 0a6b008 Author: comfyanonymous <[email protected]> Date: Sun Aug 4 10:03:33 2024 -0400 Fix issue with some custom nodes. commit 56f3c66 Author: comfyanonymous <[email protected]> Date: Sun Aug 4 04:06:00 2024 -0400 ModelSamplingFlux now takes a resolution and adjusts the shift with it. If you want to sample Flux dev exactly how the reference code does use the same resolution as your image in this node. commit f7a5107 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 16:55:38 2024 -0400 Fix crash. commit 91be9c2 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 16:34:27 2024 -0400 Tweak lowvram memory formula. commit 03c5018 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 15:14:07 2024 -0400 Lower lowvram memory to 1/3 of free memory. commit 2ba5cc8 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 15:06:40 2024 -0400 Fix some issues. commit 1e68002 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 14:50:20 2024 -0400 Cap lowvram to half of free memory. commit ba9095e Author: comfyanonymous <[email protected]> Date: Sat Aug 3 13:45:19 2024 -0400 Automatically use fp8 for diffusion model weights if: Checkpoint contains weights in fp8. There isn't enough memory to load the diffusion model in GPU vram. commit f123328 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 12:39:33 2024 -0400 Load T5 in fp8 if it's in fp8 in the Flux checkpoint. commit 63a7e8e Author: comfyanonymous <[email protected]> Date: Sat Aug 3 11:53:30 2024 -0400 More aggressive batch splitting. commit 0eea47d Author: comfyanonymous <[email protected]> Date: Sat Aug 3 03:54:38 2024 -0400 Add ModelSamplingFlux to experiment with the shift value. Default shift on Flux Schnell is 0.0 commit 7cd0cdf Author: comfyanonymous <[email protected]> Date: Fri Aug 2 23:20:30 2024 -0400 Add advanced model merge node for Flux model. commit ea03c9d Author: comfyanonymous <[email protected]> Date: Fri Aug 2 18:08:21 2024 -0400 Better per model memory usage estimations. commit 3a9ee99 Author: comfyanonymous <[email protected]> Date: Fri Aug 2 17:34:30 2024 -0400 Tweak regular SD memory formula. commit 47da42d Author: comfyanonymous <[email protected]> Date: Fri Aug 2 17:02:35 2024 -0400 Better Flux vram estimation. commit 17bbd83 Author: comfyanonymous <[email protected]> Date: Fri Aug 2 13:14:28 2024 -0400 Fix bug loading flac workflow when it contains = character. commit bfb52de Author: fgdfgfthgr-fox <[email protected]> Date: Sat Aug 3 02:29:03 2024 +1200 Lower SAG scale step for finer control (comfyanonymous#4158) * Lower SAG step for finer control Since the introduction of cfg++ which uses very low cfg value, a step of 0.1 in SAG might be too high for finer control. Even SAG of 0.1 can be too high when cfg is only 0.6, so I change the step to 0.01. * Lower PAG step as well. * Update nodes_sag.py commit eca962c Author: comfyanonymous <[email protected]> Date: Fri Aug 2 10:24:53 2024 -0400 Add FluxGuidance node. This lets you adjust the guidance on the dev model which is a parameter that is passed to the diffusion model. commit c1696cd Author: Jairo Correa <[email protected]> Date: Fri Aug 2 10:34:12 2024 -0300 Add missing import (comfyanonymous#4174) commit 369f459 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 22:19:53 2024 -0400 Fix no longer working on old pytorch. commit ce9ac2f Author: Alexander Brown <[email protected]> Date: Thu Aug 1 18:40:56 2024 -0700 Fix clip_g/clip_l mixup (comfyanonymous#4168) commit e638f28 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 21:03:26 2024 -0400 Hack to make all resolutions work on Flux models. commit a531001 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 18:53:25 2024 -0400 Add CLIPTextEncodeFlux. commit d420bc7 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 17:49:46 2024 -0400 Tweak the memory usage formulas for Flux and SD. commit d965474 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 16:39:59 2024 -0400 Make ComfyUI split batches a higher priority than weight offload. commit 1c61361 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 16:28:11 2024 -0400 Fast preview support for Flux. commit a6decf1 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 16:18:14 2024 -0400 Fix bfloat16 potentially not being enabled on mps. commit 48eb139 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 13:41:27 2024 -0400 Try to fix mac issue. commit b4f6ebb Author: comfyanonymous <[email protected]> Date: Thu Aug 1 13:33:30 2024 -0400 Rename UNETLoader node to "Load Diffusion Model". commit d7430a1 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 13:28:41 2024 -0400 Add a way to load the diffusion model in fp8 with UNETLoader node. commit f2b80f9 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 12:55:28 2024 -0400 Better Mac support on flux model. commit 1aa9cf3 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 12:11:57 2024 -0400 Make lowvram more aggressive on low memory machines. commit 2f88d19 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 11:48:19 2024 -0400 Add link to Flux examples to readme. commit eb96c3b Author: comfyanonymous <[email protected]> Date: Thu Aug 1 11:32:58 2024 -0400 Fix .sft file loading (they are safetensors files). commit 5f98de7 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 11:05:56 2024 -0400 Load flux t5 in fp8 if weights are in fp8. commit 8d34211 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 09:57:01 2024 -0400 Fix old python versions no longer working. commit 1589b58 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 04:03:59 2024 -0400 Basic Flux Schnell and Flux Dev model implementation. commit 7ad574b Author: comfyanonymous <[email protected]> Date: Thu Aug 1 09:42:17 2024 -0400 Mac supports bf16 just make sure you are using the latest pytorch. commit e2382b6 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 03:58:58 2024 -0400 Make lowvram less aggressive when there are large amounts of free memory. commit c24f897 Author: comfyanonymous <[email protected]> Date: Wed Jul 31 02:00:19 2024 -0400 Fix to get fp8 working on T5 base. commit a5991a7 Author: comfyanonymous <[email protected]> Date: Wed Jul 31 01:34:57 2024 -0400 Fix hunyuan dit text encoder weights always being in fp32. commit 2c038cc Author: comfyanonymous <[email protected]> Date: Wed Jul 31 01:32:35 2024 -0400 Lower CLIP memory usage by a bit. commit b85216a Author: comfyanonymous <[email protected]> Date: Wed Jul 31 00:52:34 2024 -0400 Lower T5 memory usage by a few hundred MB. commit 82cae45 Author: comfyanonymous <[email protected]> Date: Tue Jul 30 14:20:28 2024 -0400 Fix potential issue with non clip text embeddings. commit 25853d0 Author: comfyanonymous <[email protected]> Date: Tue Jul 30 05:03:20 2024 -0400 Use common function for casting weights to input. commit 7904063 Author: comfyanonymous <[email protected]> Date: Tue Jul 30 05:01:34 2024 -0400 Remove unnecessary code. commit 66d35c0 Author: comfyanonymous <[email protected]> Date: Mon Jul 29 20:27:40 2024 -0400 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. commit c75b506 Author: comfyanonymous <[email protected]> Date: Mon Jul 29 11:15:37 2024 -0400 Less confusing exception if pillow() function fails. commit 4ba7fa0 Author: comfyanonymous <[email protected]> Date: Sun Jul 28 01:19:20 2024 -0400 Refactor: Move sd2_clip.py to text_encoders folder. commit ab76abc Author: bymyself <[email protected]> Date: Sat Jul 27 20:34:19 2024 -0700 Active workflow use primary fg color (comfyanonymous#4090) commit 9300058 Author: Silver <[email protected]> Date: Sat Jul 27 22:19:50 2024 +0200 Add dpmpp_2s_ancestral as custom sampler (comfyanonymous#4101) Adding dpmpp_2s_ancestral as custom sampler node to enable its use with eta and s_noise when using custom sampling. commit f82d09c Author: comfyanonymous <[email protected]> Date: Sat Jul 27 04:48:19 2024 -0400 Update packaging workflow. commit e6829e7 Author: comfyanonymous <[email protected]> Date: Sat Jul 27 04:41:46 2024 -0400 Add a way to set custom dependencies in the release workflow. commit 07f6a1a Author: comfyanonymous <[email protected]> Date: Sat Jul 27 03:15:22 2024 -0400 Handle case in the updater when master branch is not in local repo. commit e746965 Author: comfyanonymous <[email protected]> Date: Sat Jul 27 01:20:18 2024 -0400 Update nightly package workflow. commit 45a2842 Author: comfyanonymous <[email protected]> Date: Fri Jul 26 14:52:00 2024 -0400 Set stable releases as a prerelease initially. This should give time to test the standalone package before making it live. commit 17b41f6 Author: Robin Huang <[email protected]> Date: Fri Jul 26 11:37:40 2024 -0700 Change windows standalone URL to stable release. (comfyanonymous#4065) commit cf4418b Author: comfyanonymous <[email protected]> Date: Fri Jul 26 13:07:39 2024 -0400 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. commit 6225a78 Author: comfyanonymous <[email protected]> Date: Fri Jul 26 13:04:48 2024 -0400 Add CLIPTextEncodeHunyuanDiT. Useful for testing what each text encoder does. commit b6779d8 Author: filtered <[email protected]> Date: Sat Jul 27 02:25:42 2024 +1000 Fix undo incorrectly undoing text input (comfyanonymous#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. commit 8328a2d Author: comfyanonymous <[email protected]> Date: Fri Jul 26 12:11:32 2024 -0400 Let hunyuan dit work with all prompt lengths. commit afe732b Author: comfyanonymous <[email protected]> Date: Fri Jul 26 11:52:58 2024 -0400 Hunyuan dit can now accept longer prompts. commit a9ac56f Author: comfyanonymous <[email protected]> Date: Fri Jul 26 04:32:33 2024 -0400 Own BertModel implementation that works with lowvram. commit 25b51b1 Author: comfyanonymous <[email protected]> Date: Thu Jul 25 22:42:54 2024 -0400 Hunyuan DiT lora support. commit 61a2b00 Author: comfyanonymous <[email protected]> Date: Thu Jul 25 19:06:43 2024 -0400 Add HunyuanDiT support to readme. commit a5f4292 Author: comfyanonymous <[email protected]> Date: Thu Jul 25 18:21:08 2024 -0400 Basic hunyuan dit implementation. (comfyanonymous#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. commit f87810c Author: comfyanonymous <[email protected]> Date: Thu Jul 25 10:52:09 2024 -0400 Let tokenizers return weights to be stored in the saved checkpoint. commit 10c919f Author: comfyanonymous <[email protected]> Date: Wed Jul 24 16:43:53 2024 -0400 Make it possible to load tokenizer data from checkpoints. commit ce80e69 Author: comfyanonymous <[email protected]> Date: Wed Jul 24 13:50:34 2024 -0400 Avoid loading the dll when it's not necessary. commit 19944ad Author: comfyanonymous <[email protected]> Date: Wed Jul 24 12:49:29 2024 -0400 Add code to fix issues with new pytorch version on the standalone. commit 10b43ce Author: comfyanonymous <[email protected]> Date: Wed Jul 24 01:12:59 2024 -0400 Remove duplicate code. commit 0a4c49c Author: comfyanonymous <[email protected]> Date: Tue Jul 23 15:35:28 2024 -0400 Support MT5. commit 88ed893 Author: comfyanonymous <[email protected]> Date: Tue Jul 23 14:17:42 2024 -0400 Allow SPieceTokenizer to load model from a byte string. commit 334ba48 Author: comfyanonymous <[email protected]> Date: Tue Jul 23 14:13:32 2024 -0400 More generic unet prefix detection code. commit 14764aa Author: comfyanonymous <[email protected]> Date: Mon Jul 22 12:21:45 2024 -0400 Rename LLAMATokenizer to SPieceTokenizer. commit b2c995f Author: comfyanonymous <[email protected]> Date: Mon Jul 22 11:30:38 2024 -0400 "auto" type is only relevant to the SetUnionControlNetType node. commit 4151fbf Author: Chenlei Hu <[email protected]> Date: Mon Jul 22 11:27:32 2024 -0400 Add error message on union controlnet (comfyanonymous#4081) commit 6045ed3 Author: Chenlei Hu <[email protected]> Date: Sun Jul 21 21:15:01 2024 -0400 Supress frontend exception on unhandled message type (comfyanonymous#4078) * Supress frontend exception on unhandled message type * nit commit f836e69 Author: comfyanonymous <[email protected]> Date: Sun Jul 21 16:16:45 2024 -0400 Fix bug with SaveAudio node with --gpu-only commit 5b69cfe Author: Chenlei Hu <[email protected]> Date: Sun Jul 21 15:29:10 2024 -0400 Add timestamp to execution messages (comfyanonymous#4076) * Add timestamp to execution messages * Add execution_end message * Rename to execution_success commit 95fa954 Author: comfyanonymous <[email protected]> Date: Sat Jul 20 12:27:42 2024 -0400 Only append zero to noise schedule if last sigma isn't zero. commit 11b7414 Author: Greg Wainer <[email protected]> Date: Fri Jul 19 17:39:04 2024 -0500 Fix/webp exif little endian (comfyanonymous#4061) * Fix for isLittleEndian flag in parseExifData. * Add break after reading first exif chunk in getWebpMetadata. commit 6ab8cad Author: comfyanonymous <[email protected]> Date: Fri Jul 19 17:44:56 2024 -0400 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. commit 011b11d Author: bymyself <[email protected]> Date: Thu Jul 18 18:59:18 2024 -0700 LoadAudio restores file value from workflow (comfyanonymous#4043) * LoadAudio restores file value from workflow * use onAfterGraphConfigured * Don't use anonnymous function commit ff6ca2a Author: comfyanonymous <[email protected]> Date: Thu Jul 18 17:20:05 2024 -0400 Move PAG to model_patches/unet section. Move other unet model_patches nodes to model_patches/unet section. commit 374e093 Author: bymyself <[email protected]> Date: Wed Jul 17 13:11:10 2024 -0700 Disable audio widget trying to get previews (comfyanonymous#4044) commit 8557894 Author: 喵哩个咪 <[email protected]> Date: Thu Jul 18 01:12:50 2024 +0800 support clip-vit-large-patch14-336 (comfyanonymous#4042) * support clip-vit-large-patch14-336 * support clip-vit-large-patch14-336 commit 6f7869f Author: comfyanonymous <[email protected]> Date: Wed Jul 17 13:05:38 2024 -0400 Get clip vision image size from config. commit 281ad42 Author: comfyanonymous <[email protected]> Date: Wed Jul 17 10:16:31 2024 -0400 Fix lowvram union controlnet bug. commit 1cde6b2 Author: Chenlei Hu <[email protected]> Date: Tue Jul 16 21:15:08 2024 -0400 Disallow use of eval with pylint (comfyanonymous#4033) commit c5a48b1 Author: Thomas Ward <[email protected]> Date: Tue Jul 16 18:27:09 2024 -0400 Make default hash lib configurable without code changes via CLI argument (comfyanonymous#3947) * cli_args: Add --duplicate-check-hash-function. * server.py: compare_image_hash configurable hash function Uses an argument added in cli_args to specify the type of hashing to default to for duplicate hash checking. Uses an `eval()` to identify the specific hashlib class to utilize, but ultimately safely operates because we have specific options and only those options/choices in the arg parser. So we don't have any unsafe input there. * Add hasher() to node_helpers * hashlib selection moved to node_helpers * default-hashing-function instead of dupe checking hasher This makes a default-hashing-function option instead of previous selected option. * Use args.default_hashing_function * Use safer handling for node_helpers.hasher() Uses a safer handling method than `eval` to evaluate default hashing function. * Stray parentheses are evil. * Indentation fix. Somehow when I hit save I didn't notice I missed a space to make indentation work proper. Oops! commit f229879 Author: Chenlei Hu <[email protected]> Date: Tue Jul 16 18:20:39 2024 -0400 Fix annotation (comfyanonymous#4035) commit 60383f3 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 17:08:25 2024 -0400 Move controlnet nodes to conditioning/controlnet. commit 8270c62 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 17:01:40 2024 -0400 Add SetUnionControlNetType to set the type of the union controlnet model. commit 821f938 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 15:18:24 2024 -0400 Allow model sampling to set number of timesteps. commit e163039 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 11:29:38 2024 -0400 Allow version names like v0.0.1 for the FrontendManager. commit 99458e8 Author: Chenlei Hu <[email protected]> Date: Tue Jul 16 11:26:11 2024 -0400 Add `FrontendManager` to manage non-default front-end impl (comfyanonymous#3897) * Add frontend manager * Add tests * nit * Add unit test to github CI * Fix path * nit * ignore * Add logging * Install test deps * Remove 'stable' keyword support * Update test * Add web-root arg * Rename web-root to front-end-root * Add test on non-exist version number * Use repo owner/name to replace hard coded provider list * Inline cmd args * nit * Fix unit test commit 33346fd Author: comfyanonymous <[email protected]> Date: Mon Jul 15 20:36:03 2024 -0400 Fix bug with custom nodes on other drives. commit 136c93c Author: comfyanonymous <[email protected]> Date: Mon Jul 15 20:01:49 2024 -0400 Fix bug with workflow not registering change. There was an issue when only the class type of a node changed with all the inputs staying the same. commit 1305fb2 Author: comfyanonymous <[email protected]> Date: Mon Jul 15 17:36:24 2024 -0400 Refactor: Move some code to the comfy/text_encoders folder. commit 7914c47 Author: comfyanonymous <[email protected]> Date: Sun Jul 14 10:07:36 2024 -0400 Quick fix for the promax controlnet. commit 79547ef Author: pythongosssss <[email protected]> Date: Sun Jul 14 07:04:40 2024 +0100 New menu fixes - fix send to workflow (comfyanonymous#3909) * Fix send to workflow Fix center align of close workflow dialog Better support for elements around canvas * More resilent to extra elements added to body commit a3dffc4 Author: comfyanonymous <[email protected]> Date: Sat Jul 13 13:51:40 2024 -0400 Support AuraFlow Lora and loading model weights in diffusers format. You can load model weights in diffusers format using the UNETLoader node. commit ce2473b Author: comfyanonymous <[email protected]> Date: Fri Jul 12 15:25:07 2024 -0400 Add link to AuraFlow example in Readme. commit 4ca9b9c Author: Robin Huang <[email protected]> Date: Fri Jul 12 10:33:57 2024 -0700 Add Github Workflow for releasing stable versions and standalone bundle. (comfyanonymous#3949) * Add stable release. * Only build CUDA 12.1 + 3.11 Python. * Upgrade checkout and setup-python to latest version. * lzma2 * Update artifact name to be ComfyUI_windows_portable_nvidia.7z commit 29c2e26 Author: comfyanonymous <[email protected]> Date: Fri Jul 12 01:08:45 2024 -0400 Better tokenizing code for AuraFlow. commit b6f09cf Author: comfyanonymous <[email protected]> Date: Thu Jul 11 22:58:03 2024 -0400 Add sentencepiece dependency. commit 8e01204 Author: comfyanonymous <[email protected]> Date: Thu Jul 11 17:51:56 2024 -0400 Add a ModelSamplingAuraFlow node to change the shift value. Set the default AuraFlow shift value to 1.73 (sqrt(3)). commit 9f291d7 Author: comfyanonymous <[email protected]> Date: Thu Jul 11 16:51:06 2024 -0400 AuraFlow model implementation. commit f45157e Author: comfyanonymous <[email protected]> Date: Thu Jul 11 11:46:51 2024 -0400 Fix error message never being shown. commit 5e1fced Author: comfyanonymous <[email protected]> Date: Thu Jul 11 11:37:31 2024 -0400 Cleaner support for loading different diffusion model types. commit ffe0bb0 Author: comfyanonymous <[email protected]> Date: Wed Jul 10 20:33:12 2024 -0400 Remove useless code. commit 391c104 Author: comfyanonymous <[email protected]> Date: Wed Jul 10 20:06:50 2024 -0400 More flexibility with text encoder return values. Text encoders can now return other values to the CONDITIONING than the cond and pooled output. commit e44fa56 Author: comfyanonymous <[email protected]> Date: Wed Jul 10 19:31:22 2024 -0400 Support returning text encoder attention masks. commit 90389b3 Author: Chenlei Hu <[email protected]> Date: Wed Jul 10 11:28:15 2024 -0400 Update bug issue template (comfyanonymous#3996) * Update issue template * nit # Conflicts: # .gitignore resolved by upstream/master version # comfy/samplers.py resolved by upstream/master version
chenbaiyujason
added a commit
to NeoWorldTeam/ComfyUI
that referenced
this pull request
Aug 10, 2024
commit ae197f6 Author: comfyanonymous <[email protected]> Date: Sat Aug 10 07:36:27 2024 -0400 Speed up hunyuan dit inference a bit. commit 1b5b8ca Author: comfyanonymous <[email protected]> Date: Fri Aug 9 21:45:21 2024 -0400 Fix regression. commit 6678d5c Author: comfyanonymous <[email protected]> Date: Fri Aug 9 14:02:38 2024 -0400 Fix regression. commit e172564 Author: TTPlanetPig <[email protected]> Date: Sat Aug 10 01:40:05 2024 +0800 Update controlnet.py to fix the default controlnet weight as constant (comfyanonymous#4285) commit a3cc326 Author: comfyanonymous <[email protected]> Date: Fri Aug 9 12:16:25 2024 -0400 Better fix for lowvram issue. commit 86a97e9 Author: comfyanonymous <[email protected]> Date: Fri Aug 9 12:08:58 2024 -0400 Fix controlnet regression. commit 5acdadc Author: comfyanonymous <[email protected]> Date: Fri Aug 9 03:58:28 2024 -0400 Fix issue with some lowvram weights. commit 55ad9d5 Author: comfyanonymous <[email protected]> Date: Fri Aug 9 03:36:40 2024 -0400 Fix regression. commit a9f04ed Author: comfyanonymous <[email protected]> Date: Fri Aug 9 03:21:10 2024 -0400 Implement text encoder part of HunyuanDiT loras. commit a475ec2 Author: comfyanonymous <[email protected]> Date: Fri Aug 9 02:35:19 2024 -0400 Cleanup HunyuanDit controlnets. Use the: ControlNetApply SD3 and HunyuanDiT node. commit 06eb9fb Author: 来新璐 <[email protected]> Date: Fri Aug 9 14:59:24 2024 +0800 feat: add support for HunYuanDit ControlNet (comfyanonymous#4245) * add support for HunYuanDit ControlNet * fix hunyuandit controlnet * fix typo in hunyuandit controlnet * fix typo in hunyuandit controlnet * fix code format style * add control_weight support for HunyuanDit Controlnet * use control_weights in HunyuanDit Controlnet * fix typo commit 4133226 Author: comfyanonymous <[email protected]> Date: Thu Aug 8 22:09:29 2024 -0400 Raw torch is faster than einops? commit 11200de Author: comfyanonymous <[email protected]> Date: Thu Aug 8 20:07:09 2024 -0400 Cleaner code. commit 037c38e Author: comfyanonymous <[email protected]> Date: Thu Aug 8 17:28:35 2024 -0400 Try to improve inference speed on some machines. commit 1e11d2d Author: comfyanonymous <[email protected]> Date: Thu Aug 8 17:05:16 2024 -0400 Better prints. commit 65ea6be Author: Alex "mcmonkey" Goodwin <[email protected]> Date: Thu Aug 8 14:20:48 2024 -0700 PullRequest CI Run: use pull_request_target to allow the CI Dashboard to work (comfyanonymous#4277) '_target' allows secrets to pass through, and we're just using the secret that allows uploading to the dashboard and are manually vetting PRs before running this workflow anyway commit 5df6f57 Author: Alex "mcmonkey" Goodwin <[email protected]> Date: Thu Aug 8 13:30:59 2024 -0700 minor fix on copypasta action name (comfyanonymous#4276) my bad sorry commit 6588bfd Author: Alex "mcmonkey" Goodwin <[email protected]> Date: Thu Aug 8 13:24:49 2024 -0700 add GitHub workflow for CI tests of PRs (comfyanonymous#4275) When the 'Run-CI-Test' label is added to a PR, it will be tested by the CI, on a small matrix of stable versions. commit 50ed287 Author: Alex "mcmonkey" Goodwin <[email protected]> Date: Thu Aug 8 12:40:07 2024 -0700 Add full CI test matrix GitHub Workflow (comfyanonymous#4274) automatically runs a matrix of full GPU-enabled tests on all new commits to the ComfyUI master branch commit 66d4233 Author: comfyanonymous <[email protected]> Date: Thu Aug 8 15:16:51 2024 -0400 Fix. commit 591010b Author: comfyanonymous <[email protected]> Date: Thu Aug 8 14:45:52 2024 -0400 Support diffusers text attention flux loras. commit 08f92d5 Author: comfyanonymous <[email protected]> Date: Thu Aug 8 03:27:37 2024 -0400 Partial model shift support. commit 8115d8c Author: comfyanonymous <[email protected]> Date: Wed Aug 7 15:08:39 2024 -0400 Add Flux fp16 support hack. commit 6969fc9 Author: comfyanonymous <[email protected]> Date: Wed Aug 7 15:00:06 2024 -0400 Make supported_dtypes a priority list. commit cb7c4b4 Author: comfyanonymous <[email protected]> Date: Wed Aug 7 14:30:54 2024 -0400 Workaround for lora OOM on lowvram mode. commit 1208863 Author: comfyanonymous <[email protected]> Date: Wed Aug 7 13:49:31 2024 -0400 Fix "Comfy" lora keys. They are in this format now: diffusion_model.full.model.key.name.lora_up.weight commit e1c5281 Author: comfyanonymous <[email protected]> Date: Wed Aug 7 13:30:45 2024 -0400 Fix bundled embed. commit 17030fd Author: comfyanonymous <[email protected]> Date: Wed Aug 7 13:18:32 2024 -0400 Support for "Comfy" lora format. The keys are just: model.full.model.key.name.lora_up.weight It is supported by all comfyui supported models. Now people can just convert loras to this format instead of having to ask for me to implement them. commit c19dcd3 Author: comfyanonymous <[email protected]> Date: Wed Aug 7 12:59:28 2024 -0400 Controlnet code refactor. commit 1c08bf3 Author: comfyanonymous <[email protected]> Date: Wed Aug 7 03:45:25 2024 -0400 Support format for embeddings bundled in loras. commit 2a02546 Author: PhilWun <[email protected]> Date: Wed Aug 7 03:59:34 2024 +0200 Add type hints to folder_paths.py (comfyanonymous#4191) * add type hints to folder_paths.py * replace deprecated standard collections type hints * fix type error when using Python 3.8 commit b334605 Author: comfyanonymous <[email protected]> Date: Tue Aug 6 13:27:48 2024 -0400 Fix OOMs happening in some cases. A cloned model patcher sometimes reported a model was loaded on a device when it wasn't. commit de17a97 Author: comfyanonymous <[email protected]> Date: Tue Aug 6 03:30:28 2024 -0400 Unload all models if there's an OOM error. commit c14ac98 Author: comfyanonymous <[email protected]> Date: Tue Aug 6 03:22:39 2024 -0400 Unload models and load them back in lowvram mode no free vram. commit 2894511 Author: Robin Huang <[email protected]> Date: Mon Aug 5 22:46:09 2024 -0700 Clone taesd with depth of 1 to reduce download size. (comfyanonymous#4232) commit f3bc402 Author: Silver <[email protected]> Date: Tue Aug 6 07:45:24 2024 +0200 Add format metadata to CLIP save to make compatible with diffusers safetensors loading (comfyanonymous#4233) commit 841e74a Author: Chenlei Hu <[email protected]> Date: Tue Aug 6 01:27:28 2024 -0400 Change browser test CI python to 3.8 (comfyanonymous#4234) commit 2d75df4 Author: comfyanonymous <[email protected]> Date: Mon Aug 5 21:58:28 2024 -0400 Flux tweak memory usage. commit 1abc9c8 Author: Robin Huang <[email protected]> Date: Mon Aug 5 17:07:16 2024 -0700 Stable release uses cached dependencies (comfyanonymous#4231) * Release stable based on existing tag. * Update default cuda to 12.1. commit 8edbcf5 Author: comfyanonymous <[email protected]> Date: Mon Aug 5 16:24:04 2024 -0400 Improve performance on some lowend GPUs. commit e545a63 Author: comfyanonymous <[email protected]> Date: Mon Aug 5 12:31:12 2024 -0400 This probably doesn't work anymore. commit 33e5203 Author: bymyself <[email protected]> Date: Mon Aug 5 09:25:28 2024 -0700 Don't cache index.html (comfyanonymous#4211) commit a178e25 Author: a-One-Fan <[email protected]> Date: Mon Aug 5 08:26:20 2024 +0300 Fix Flux FP64 math on XPU (comfyanonymous#4210) commit 78e133d Author: comfyanonymous <[email protected]> Date: Sun Aug 4 21:59:42 2024 -0400 Support simple diffusers Flux loras. commit 7afa985 Author: Silver <[email protected]> Date: Sun Aug 4 23:10:02 2024 +0200 Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' (comfyanonymous#4200) commit ddb6a9f Author: comfyanonymous <[email protected]> Date: Sun Aug 4 15:59:02 2024 -0400 Set the step in EmptySD3LatentImage to 16. These models work better when the res is a multiple of 16. commit 3b71f84 Author: comfyanonymous <[email protected]> Date: Sun Aug 4 15:45:43 2024 -0400 ONNX tracing fixes. commit 0a6b008 Author: comfyanonymous <[email protected]> Date: Sun Aug 4 10:03:33 2024 -0400 Fix issue with some custom nodes. commit 56f3c66 Author: comfyanonymous <[email protected]> Date: Sun Aug 4 04:06:00 2024 -0400 ModelSamplingFlux now takes a resolution and adjusts the shift with it. If you want to sample Flux dev exactly how the reference code does use the same resolution as your image in this node. commit f7a5107 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 16:55:38 2024 -0400 Fix crash. commit 91be9c2 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 16:34:27 2024 -0400 Tweak lowvram memory formula. commit 03c5018 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 15:14:07 2024 -0400 Lower lowvram memory to 1/3 of free memory. commit 2ba5cc8 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 15:06:40 2024 -0400 Fix some issues. commit 1e68002 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 14:50:20 2024 -0400 Cap lowvram to half of free memory. commit ba9095e Author: comfyanonymous <[email protected]> Date: Sat Aug 3 13:45:19 2024 -0400 Automatically use fp8 for diffusion model weights if: Checkpoint contains weights in fp8. There isn't enough memory to load the diffusion model in GPU vram. commit f123328 Author: comfyanonymous <[email protected]> Date: Sat Aug 3 12:39:33 2024 -0400 Load T5 in fp8 if it's in fp8 in the Flux checkpoint. commit 63a7e8e Author: comfyanonymous <[email protected]> Date: Sat Aug 3 11:53:30 2024 -0400 More aggressive batch splitting. commit 0eea47d Author: comfyanonymous <[email protected]> Date: Sat Aug 3 03:54:38 2024 -0400 Add ModelSamplingFlux to experiment with the shift value. Default shift on Flux Schnell is 0.0 commit 7cd0cdf Author: comfyanonymous <[email protected]> Date: Fri Aug 2 23:20:30 2024 -0400 Add advanced model merge node for Flux model. commit ea03c9d Author: comfyanonymous <[email protected]> Date: Fri Aug 2 18:08:21 2024 -0400 Better per model memory usage estimations. commit 3a9ee99 Author: comfyanonymous <[email protected]> Date: Fri Aug 2 17:34:30 2024 -0400 Tweak regular SD memory formula. commit 47da42d Author: comfyanonymous <[email protected]> Date: Fri Aug 2 17:02:35 2024 -0400 Better Flux vram estimation. commit 17bbd83 Author: comfyanonymous <[email protected]> Date: Fri Aug 2 13:14:28 2024 -0400 Fix bug loading flac workflow when it contains = character. commit bfb52de Author: fgdfgfthgr-fox <[email protected]> Date: Sat Aug 3 02:29:03 2024 +1200 Lower SAG scale step for finer control (comfyanonymous#4158) * Lower SAG step for finer control Since the introduction of cfg++ which uses very low cfg value, a step of 0.1 in SAG might be too high for finer control. Even SAG of 0.1 can be too high when cfg is only 0.6, so I change the step to 0.01. * Lower PAG step as well. * Update nodes_sag.py commit eca962c Author: comfyanonymous <[email protected]> Date: Fri Aug 2 10:24:53 2024 -0400 Add FluxGuidance node. This lets you adjust the guidance on the dev model which is a parameter that is passed to the diffusion model. commit c1696cd Author: Jairo Correa <[email protected]> Date: Fri Aug 2 10:34:12 2024 -0300 Add missing import (comfyanonymous#4174) commit 369f459 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 22:19:53 2024 -0400 Fix no longer working on old pytorch. commit ce9ac2f Author: Alexander Brown <[email protected]> Date: Thu Aug 1 18:40:56 2024 -0700 Fix clip_g/clip_l mixup (comfyanonymous#4168) commit e638f28 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 21:03:26 2024 -0400 Hack to make all resolutions work on Flux models. commit a531001 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 18:53:25 2024 -0400 Add CLIPTextEncodeFlux. commit d420bc7 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 17:49:46 2024 -0400 Tweak the memory usage formulas for Flux and SD. commit d965474 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 16:39:59 2024 -0400 Make ComfyUI split batches a higher priority than weight offload. commit 1c61361 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 16:28:11 2024 -0400 Fast preview support for Flux. commit a6decf1 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 16:18:14 2024 -0400 Fix bfloat16 potentially not being enabled on mps. commit 48eb139 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 13:41:27 2024 -0400 Try to fix mac issue. commit b4f6ebb Author: comfyanonymous <[email protected]> Date: Thu Aug 1 13:33:30 2024 -0400 Rename UNETLoader node to "Load Diffusion Model". commit d7430a1 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 13:28:41 2024 -0400 Add a way to load the diffusion model in fp8 with UNETLoader node. commit f2b80f9 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 12:55:28 2024 -0400 Better Mac support on flux model. commit 1aa9cf3 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 12:11:57 2024 -0400 Make lowvram more aggressive on low memory machines. commit 2f88d19 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 11:48:19 2024 -0400 Add link to Flux examples to readme. commit eb96c3b Author: comfyanonymous <[email protected]> Date: Thu Aug 1 11:32:58 2024 -0400 Fix .sft file loading (they are safetensors files). commit 5f98de7 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 11:05:56 2024 -0400 Load flux t5 in fp8 if weights are in fp8. commit 8d34211 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 09:57:01 2024 -0400 Fix old python versions no longer working. commit 1589b58 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 04:03:59 2024 -0400 Basic Flux Schnell and Flux Dev model implementation. commit 7ad574b Author: comfyanonymous <[email protected]> Date: Thu Aug 1 09:42:17 2024 -0400 Mac supports bf16 just make sure you are using the latest pytorch. commit e2382b6 Author: comfyanonymous <[email protected]> Date: Thu Aug 1 03:58:58 2024 -0400 Make lowvram less aggressive when there are large amounts of free memory. commit c24f897 Author: comfyanonymous <[email protected]> Date: Wed Jul 31 02:00:19 2024 -0400 Fix to get fp8 working on T5 base. commit a5991a7 Author: comfyanonymous <[email protected]> Date: Wed Jul 31 01:34:57 2024 -0400 Fix hunyuan dit text encoder weights always being in fp32. commit 2c038cc Author: comfyanonymous <[email protected]> Date: Wed Jul 31 01:32:35 2024 -0400 Lower CLIP memory usage by a bit. commit b85216a Author: comfyanonymous <[email protected]> Date: Wed Jul 31 00:52:34 2024 -0400 Lower T5 memory usage by a few hundred MB. commit 82cae45 Author: comfyanonymous <[email protected]> Date: Tue Jul 30 14:20:28 2024 -0400 Fix potential issue with non clip text embeddings. commit 25853d0 Author: comfyanonymous <[email protected]> Date: Tue Jul 30 05:03:20 2024 -0400 Use common function for casting weights to input. commit 7904063 Author: comfyanonymous <[email protected]> Date: Tue Jul 30 05:01:34 2024 -0400 Remove unnecessary code. commit 66d35c0 Author: comfyanonymous <[email protected]> Date: Mon Jul 29 20:27:40 2024 -0400 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. commit c75b506 Author: comfyanonymous <[email protected]> Date: Mon Jul 29 11:15:37 2024 -0400 Less confusing exception if pillow() function fails. commit 4ba7fa0 Author: comfyanonymous <[email protected]> Date: Sun Jul 28 01:19:20 2024 -0400 Refactor: Move sd2_clip.py to text_encoders folder. commit ab76abc Author: bymyself <[email protected]> Date: Sat Jul 27 20:34:19 2024 -0700 Active workflow use primary fg color (comfyanonymous#4090) commit 9300058 Author: Silver <[email protected]> Date: Sat Jul 27 22:19:50 2024 +0200 Add dpmpp_2s_ancestral as custom sampler (comfyanonymous#4101) Adding dpmpp_2s_ancestral as custom sampler node to enable its use with eta and s_noise when using custom sampling. commit f82d09c Author: comfyanonymous <[email protected]> Date: Sat Jul 27 04:48:19 2024 -0400 Update packaging workflow. commit e6829e7 Author: comfyanonymous <[email protected]> Date: Sat Jul 27 04:41:46 2024 -0400 Add a way to set custom dependencies in the release workflow. commit 07f6a1a Author: comfyanonymous <[email protected]> Date: Sat Jul 27 03:15:22 2024 -0400 Handle case in the updater when master branch is not in local repo. commit e746965 Author: comfyanonymous <[email protected]> Date: Sat Jul 27 01:20:18 2024 -0400 Update nightly package workflow. commit 45a2842 Author: comfyanonymous <[email protected]> Date: Fri Jul 26 14:52:00 2024 -0400 Set stable releases as a prerelease initially. This should give time to test the standalone package before making it live. commit 17b41f6 Author: Robin Huang <[email protected]> Date: Fri Jul 26 11:37:40 2024 -0700 Change windows standalone URL to stable release. (comfyanonymous#4065) commit cf4418b Author: comfyanonymous <[email protected]> Date: Fri Jul 26 13:07:39 2024 -0400 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. commit 6225a78 Author: comfyanonymous <[email protected]> Date: Fri Jul 26 13:04:48 2024 -0400 Add CLIPTextEncodeHunyuanDiT. Useful for testing what each text encoder does. commit b6779d8 Author: filtered <[email protected]> Date: Sat Jul 27 02:25:42 2024 +1000 Fix undo incorrectly undoing text input (comfyanonymous#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. commit 8328a2d Author: comfyanonymous <[email protected]> Date: Fri Jul 26 12:11:32 2024 -0400 Let hunyuan dit work with all prompt lengths. commit afe732b Author: comfyanonymous <[email protected]> Date: Fri Jul 26 11:52:58 2024 -0400 Hunyuan dit can now accept longer prompts. commit a9ac56f Author: comfyanonymous <[email protected]> Date: Fri Jul 26 04:32:33 2024 -0400 Own BertModel implementation that works with lowvram. commit 25b51b1 Author: comfyanonymous <[email protected]> Date: Thu Jul 25 22:42:54 2024 -0400 Hunyuan DiT lora support. commit 61a2b00 Author: comfyanonymous <[email protected]> Date: Thu Jul 25 19:06:43 2024 -0400 Add HunyuanDiT support to readme. commit a5f4292 Author: comfyanonymous <[email protected]> Date: Thu Jul 25 18:21:08 2024 -0400 Basic hunyuan dit implementation. (comfyanonymous#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. commit f87810c Author: comfyanonymous <[email protected]> Date: Thu Jul 25 10:52:09 2024 -0400 Let tokenizers return weights to be stored in the saved checkpoint. commit 10c919f Author: comfyanonymous <[email protected]> Date: Wed Jul 24 16:43:53 2024 -0400 Make it possible to load tokenizer data from checkpoints. commit ce80e69 Author: comfyanonymous <[email protected]> Date: Wed Jul 24 13:50:34 2024 -0400 Avoid loading the dll when it's not necessary. commit 19944ad Author: comfyanonymous <[email protected]> Date: Wed Jul 24 12:49:29 2024 -0400 Add code to fix issues with new pytorch version on the standalone. commit 10b43ce Author: comfyanonymous <[email protected]> Date: Wed Jul 24 01:12:59 2024 -0400 Remove duplicate code. commit 0a4c49c Author: comfyanonymous <[email protected]> Date: Tue Jul 23 15:35:28 2024 -0400 Support MT5. commit 88ed893 Author: comfyanonymous <[email protected]> Date: Tue Jul 23 14:17:42 2024 -0400 Allow SPieceTokenizer to load model from a byte string. commit 334ba48 Author: comfyanonymous <[email protected]> Date: Tue Jul 23 14:13:32 2024 -0400 More generic unet prefix detection code. commit 14764aa Author: comfyanonymous <[email protected]> Date: Mon Jul 22 12:21:45 2024 -0400 Rename LLAMATokenizer to SPieceTokenizer. commit b2c995f Author: comfyanonymous <[email protected]> Date: Mon Jul 22 11:30:38 2024 -0400 "auto" type is only relevant to the SetUnionControlNetType node. commit 4151fbf Author: Chenlei Hu <[email protected]> Date: Mon Jul 22 11:27:32 2024 -0400 Add error message on union controlnet (comfyanonymous#4081) commit 6045ed3 Author: Chenlei Hu <[email protected]> Date: Sun Jul 21 21:15:01 2024 -0400 Supress frontend exception on unhandled message type (comfyanonymous#4078) * Supress frontend exception on unhandled message type * nit commit f836e69 Author: comfyanonymous <[email protected]> Date: Sun Jul 21 16:16:45 2024 -0400 Fix bug with SaveAudio node with --gpu-only commit 5b69cfe Author: Chenlei Hu <[email protected]> Date: Sun Jul 21 15:29:10 2024 -0400 Add timestamp to execution messages (comfyanonymous#4076) * Add timestamp to execution messages * Add execution_end message * Rename to execution_success commit 95fa954 Author: comfyanonymous <[email protected]> Date: Sat Jul 20 12:27:42 2024 -0400 Only append zero to noise schedule if last sigma isn't zero. commit 11b7414 Author: Greg Wainer <[email protected]> Date: Fri Jul 19 17:39:04 2024 -0500 Fix/webp exif little endian (comfyanonymous#4061) * Fix for isLittleEndian flag in parseExifData. * Add break after reading first exif chunk in getWebpMetadata. commit 6ab8cad Author: comfyanonymous <[email protected]> Date: Fri Jul 19 17:44:56 2024 -0400 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. commit 011b11d Author: bymyself <[email protected]> Date: Thu Jul 18 18:59:18 2024 -0700 LoadAudio restores file value from workflow (comfyanonymous#4043) * LoadAudio restores file value from workflow * use onAfterGraphConfigured * Don't use anonnymous function commit ff6ca2a Author: comfyanonymous <[email protected]> Date: Thu Jul 18 17:20:05 2024 -0400 Move PAG to model_patches/unet section. Move other unet model_patches nodes to model_patches/unet section. commit 374e093 Author: bymyself <[email protected]> Date: Wed Jul 17 13:11:10 2024 -0700 Disable audio widget trying to get previews (comfyanonymous#4044) commit 8557894 Author: 喵哩个咪 <[email protected]> Date: Thu Jul 18 01:12:50 2024 +0800 support clip-vit-large-patch14-336 (comfyanonymous#4042) * support clip-vit-large-patch14-336 * support clip-vit-large-patch14-336 commit 6f7869f Author: comfyanonymous <[email protected]> Date: Wed Jul 17 13:05:38 2024 -0400 Get clip vision image size from config. commit 281ad42 Author: comfyanonymous <[email protected]> Date: Wed Jul 17 10:16:31 2024 -0400 Fix lowvram union controlnet bug. commit 1cde6b2 Author: Chenlei Hu <[email protected]> Date: Tue Jul 16 21:15:08 2024 -0400 Disallow use of eval with pylint (comfyanonymous#4033) commit c5a48b1 Author: Thomas Ward <[email protected]> Date: Tue Jul 16 18:27:09 2024 -0400 Make default hash lib configurable without code changes via CLI argument (comfyanonymous#3947) * cli_args: Add --duplicate-check-hash-function. * server.py: compare_image_hash configurable hash function Uses an argument added in cli_args to specify the type of hashing to default to for duplicate hash checking. Uses an `eval()` to identify the specific hashlib class to utilize, but ultimately safely operates because we have specific options and only those options/choices in the arg parser. So we don't have any unsafe input there. * Add hasher() to node_helpers * hashlib selection moved to node_helpers * default-hashing-function instead of dupe checking hasher This makes a default-hashing-function option instead of previous selected option. * Use args.default_hashing_function * Use safer handling for node_helpers.hasher() Uses a safer handling method than `eval` to evaluate default hashing function. * Stray parentheses are evil. * Indentation fix. Somehow when I hit save I didn't notice I missed a space to make indentation work proper. Oops! commit f229879 Author: Chenlei Hu <[email protected]> Date: Tue Jul 16 18:20:39 2024 -0400 Fix annotation (comfyanonymous#4035) commit 60383f3 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 17:08:25 2024 -0400 Move controlnet nodes to conditioning/controlnet. commit 8270c62 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 17:01:40 2024 -0400 Add SetUnionControlNetType to set the type of the union controlnet model. commit 821f938 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 15:18:24 2024 -0400 Allow model sampling to set number of timesteps. commit e163039 Author: comfyanonymous <[email protected]> Date: Tue Jul 16 11:29:38 2024 -0400 Allow version names like v0.0.1 for the FrontendManager. commit 99458e8 Author: Chenlei Hu <[email protected]> Date: Tue Jul 16 11:26:11 2024 -0400 Add `FrontendManager` to manage non-default front-end impl (comfyanonymous#3897) * Add frontend manager * Add tests * nit * Add unit test to github CI * Fix path * nit * ignore * Add logging * Install test deps * Remove 'stable' keyword support * Update test * Add web-root arg * Rename web-root to front-end-root * Add test on non-exist version number * Use repo owner/name to replace hard coded provider list * Inline cmd args * nit * Fix unit test commit 33346fd Author: comfyanonymous <[email protected]> Date: Mon Jul 15 20:36:03 2024 -0400 Fix bug with custom nodes on other drives. commit 136c93c Author: comfyanonymous <[email protected]> Date: Mon Jul 15 20:01:49 2024 -0400 Fix bug with workflow not registering change. There was an issue when only the class type of a node changed with all the inputs staying the same. commit 1305fb2 Author: comfyanonymous <[email protected]> Date: Mon Jul 15 17:36:24 2024 -0400 Refactor: Move some code to the comfy/text_encoders folder. commit 7914c47 Author: comfyanonymous <[email protected]> Date: Sun Jul 14 10:07:36 2024 -0400 Quick fix for the promax controlnet. commit 79547ef Author: pythongosssss <[email protected]> Date: Sun Jul 14 07:04:40 2024 +0100 New menu fixes - fix send to workflow (comfyanonymous#3909) * Fix send to workflow Fix center align of close workflow dialog Better support for elements around canvas * More resilent to extra elements added to body commit a3dffc4 Author: comfyanonymous <[email protected]> Date: Sat Jul 13 13:51:40 2024 -0400 Support AuraFlow Lora and loading model weights in diffusers format. You can load model weights in diffusers format using the UNETLoader node. commit ce2473b Author: comfyanonymous <[email protected]> Date: Fri Jul 12 15:25:07 2024 -0400 Add link to AuraFlow example in Readme. commit 4ca9b9c Author: Robin Huang <[email protected]> Date: Fri Jul 12 10:33:57 2024 -0700 Add Github Workflow for releasing stable versions and standalone bundle. (comfyanonymous#3949) * Add stable release. * Only build CUDA 12.1 + 3.11 Python. * Upgrade checkout and setup-python to latest version. * lzma2 * Update artifact name to be ComfyUI_windows_portable_nvidia.7z commit 29c2e26 Author: comfyanonymous <[email protected]> Date: Fri Jul 12 01:08:45 2024 -0400 Better tokenizing code for AuraFlow. commit b6f09cf Author: comfyanonymous <[email protected]> Date: Thu Jul 11 22:58:03 2024 -0400 Add sentencepiece dependency. commit 8e01204 Author: comfyanonymous <[email protected]> Date: Thu Jul 11 17:51:56 2024 -0400 Add a ModelSamplingAuraFlow node to change the shift value. Set the default AuraFlow shift value to 1.73 (sqrt(3)). commit 9f291d7 Author: comfyanonymous <[email protected]> Date: Thu Jul 11 16:51:06 2024 -0400 AuraFlow model implementation. commit f45157e Author: comfyanonymous <[email protected]> Date: Thu Jul 11 11:46:51 2024 -0400 Fix error message never being shown. commit 5e1fced Author: comfyanonymous <[email protected]> Date: Thu Jul 11 11:37:31 2024 -0400 Cleaner support for loading different diffusion model types. commit ffe0bb0 Author: comfyanonymous <[email protected]> Date: Wed Jul 10 20:33:12 2024 -0400 Remove useless code. commit 391c104 Author: comfyanonymous <[email protected]> Date: Wed Jul 10 20:06:50 2024 -0400 More flexibility with text encoder return values. Text encoders can now return other values to the CONDITIONING than the cond and pooled output. commit e44fa56 Author: comfyanonymous <[email protected]> Date: Wed Jul 10 19:31:22 2024 -0400 Support returning text encoder attention masks. commit 90389b3 Author: Chenlei Hu <[email protected]> Date: Wed Jul 10 11:28:15 2024 -0400 Update bug issue template (comfyanonymous#3996) * Update issue template * nit # Conflicts: # comfy/controlnet.py resolved by upstream/master version # comfy/ldm/flux/layers.py resolved by upstream/master version # comfy/ldm/hydit/attn_layers.py resolved by upstream/master version # comfy/ldm/hydit/models.py resolved by upstream/master version # comfy/model_detection.py resolved by upstream/master version # comfy/model_management.py resolved by upstream/master version # comfy/supported_models.py resolved by upstream/master version # comfy/utils.py resolved by upstream/master version # comfy_extras/nodes_hunyuan.py resolved by upstream/master version # folder_paths.py resolved by upstream/master version
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
v*