Commit Graph

  • 75ebd963ce support ascend npu statelesshz 2024-10-30 10:04:31 +0800
  • f04ad04b65 remove unused import bezo97 2024-12-25 22:05:56 +0100
  • ceee378d86 replace 'diffusion_model' with 'transformer' rickard 2024-12-25 18:04:56 +0100
  • e10cbaddea Merge remote-tracking branch 'origin/master' into feature/custom_workflow_templates bezo97 2024-12-25 15:46:47 +0100
  • fc14655ac4 refactor into custom_node_manager, add test bezo97 2024-12-25 15:45:08 +0100
  • 0f808a62df
    Add import base64 Maruhi 2024-12-25 20:58:00 +0900
  • 61ad962154
    Update server.py Maruhi 2024-12-25 20:39:06 +0900
  • 19a64d6291 Cleanup some mac related code. comfyanonymous 2024-12-25 05:32:51 -0500
  • b486885e08 Disable bfloat16 on older mac. comfyanonymous 2024-12-25 05:18:50 -0500
  • 0229228f3f Clean up the VAE dtypes code. comfyanonymous 2024-12-25 04:50:34 -0500
  • 1ed75ab30e Update nightly pytorch instructions in readme for nvidia. comfyanonymous 2024-12-25 03:29:03 -0500
  • 99a1fb6027 Make fast fp8 take a bit less peak memory. comfyanonymous 2024-12-24 18:05:19 -0500
  • b0d8059f9f
    Update main.py Lucas - BLOCK33 2024-12-24 18:56:41 -0300
  • 1d3e8377e6 modified: main.py tonynoce 2024-12-24 16:57:11 -0300
  • 7be71a8142 Rename kl_optimal_schedule to kl_optimal_scheduler to be more consistent blepping 2024-12-24 10:50:08 -0700
  • 2992402051 Add kl_optimal scheduler blepping 2024-12-24 10:08:09 -0700
  • 1741ad55ac
    added ability to specify custom "prompt_id" bigcat88 2024-12-24 18:54:43 +0200
  • 1f6ab7dbfb
    support for "unload_models" flag when creating a task bigcat88 2024-12-24 17:41:49 +0200
  • 73e04987f7 Prevent black images in VAE Decode (Tiled) node. comfyanonymous 2024-12-24 07:36:30 -0500
  • 5388df784a Add temporal tiling to VAE Encode (Tiled) node. comfyanonymous 2024-12-24 07:10:09 -0500
  • 26e0ba8f8c
    Enable External Event Loop Integration for ComfyUI [refactor] (#6114) Alexander Piskun 2024-12-24 14:38:52 +0300
  • 0e9e3f4e6b
    Merge efa53c9e92 into bc6dac4327 Alex "mcmonkey" Goodwin 2024-12-24 11:37:10 +0800
  • bc6dac4327 Add temporal tiling to VAE Decode (Tiled) node. comfyanonymous 2024-12-23 20:03:37 -0500
  • 547eb21d06 serve workflow templates from custom_nodes bezo97 2024-12-23 23:51:24 +0100
  • ce5afecc36
    Only use events for devices supporting nonblocking Austin Mroz 2024-12-23 16:43:43 -0600
  • b6e3bc2451 add GET /workflow_templates bezo97 2024-12-23 20:15:51 +0100
  • 711d5b09c6 Attempt to fix hooks being disabled at first step of second sampler catboxanon 2024-12-23 12:45:56 -0500
  • f18ebbd316
    Use raw dir name to serve static web content (#6107) Chenlei Hu 2024-12-23 03:29:42 -0500
  • 15564688ed Add a try except block so if torch version is weird it won't crash. comfyanonymous 2024-12-23 03:22:48 -0500
  • 21f20638bd move code to model_lora_keys_unet rickard 2024-12-23 09:20:22 +0100
  • c6b9c11ef6
    Add oneAPI device selector for xpu and some other changes. (#6112) Simon Lui 2024-12-23 00:18:32 -0800
  • 31b6852f19 load ltx loras trained with finetrainers rickard 2024-12-23 08:19:34 +0100
  • e44d0ac7f7 Make --novram completely offload weights. comfyanonymous 2024-12-23 01:50:11 -0500
  • 56bc64f351 Comment out some useless code. comfyanonymous 2024-12-22 23:51:14 -0500
  • f7d83b72e0
    fixed a bug in ldm/pixart/blocks.py (#6158) zhangp365 2024-12-23 12:44:20 +0800
  • 80f07952d2 Fix lowvram issue with ltxv vae. comfyanonymous 2024-12-22 23:20:17 -0500
  • ccdd4a64ea
    fixed a bug in ldm/pixart/blocks.py zhangp365 2024-12-22 20:20:48 +0800
  • 57f330caf9 Relax minimum ratio of weights loaded in memory on nvidia. comfyanonymous 2024-12-22 03:06:37 -0500
  • 601ff9e3db Add that Hunyuan Video and Pixart are supported to readme. comfyanonymous 2024-12-21 11:31:39 -0500
  • 341667c4d5
    remove minimum step count for AYS (#6137) TechnoByte 2024-12-21 16:05:09 +0100
  • 813b8df872
    Fix race condition in preview code. Austin Mroz 2024-12-19 13:17:00 -0600
  • 228704b77c chore(pyproject): Add pyproject.toml for Custom Node Registry snomiao 2024-12-21 02:23:04 +0000
  • 5d8a211e84 chore(publish): Add Github Action for Publishing to Comfy Registry snomiao 2024-12-21 02:23:03 +0000
  • 1419dee915
    Update README.md for Intel GPUs (#6069) Qiacheng Li 2024-12-20 15:04:03 -0800
  • da13b6b827 Get rid of meshgrid warning. comfyanonymous 2024-12-20 18:02:12 -0500
  • c86cd58573 Remove useless code. comfyanonymous 2024-12-20 17:50:03 -0500
  • b5fe39211a Remove some useless code. comfyanonymous 2024-12-20 17:43:50 -0500
  • e946667216 Some fixes/cleanups to pixart code. comfyanonymous 2024-12-20 17:10:52 -0500
  • 895e78edc3 Undo changes to README.md. Simon Lui 2024-12-20 13:30:09 -0800
  • d7969cb070
    Replace print with logging (#6138) Chenlei Hu 2024-12-20 13:24:55 -0800
  • e8274e9304 nit huchenlei 2024-12-20 12:50:46 -0800
  • 62905871cc nit huchenlei 2024-12-20 12:46:24 -0800
  • 8dfda4f6c8 nit huchenlei 2024-12-20 12:44:56 -0800
  • 923c5ca8de nit huchenlei 2024-12-20 09:51:03 -0800
  • d7da99a138 nit huchenlei 2024-12-20 09:50:05 -0800
  • 678ac2ffc9 nit huchenlei 2024-12-20 09:48:57 -0800
  • b356655340 Replace print with logging huchenlei 2024-12-20 09:46:20 -0800
  • bddb02660c
    Add PixArt model support (#6055) City 2024-12-20 21:25:00 +0100
  • ca9b1b18e6
    Update symmetric_patchifier.py Miklos Nagy 2024-12-20 19:29:20 +0100
  • 09853b5e6e
    remove minimum step count for AYS TechnoByte 2024-12-20 18:36:17 +0100
  • 418eb7062d Support new LTXV VAE. v0.3.9 comfyanonymous 2024-12-20 04:38:29 -0500
  • d6edc2c53c
    refactor: moved logic of "post_prompt" endpoint to sub-function bigcat88 2024-12-20 09:41:28 +0200
  • cac68ca813 Fix some more video tiled encode issues. comfyanonymous 2024-12-19 23:14:03 -0500
  • 52c1d933b2 Fix tiled hunyuan video VAE encode issue. comfyanonymous 2024-12-19 22:52:37 -0500
  • 3cacd3fca5
    Support preview images embedded in safetensors metadata (#6119) catboxanon 2024-12-19 17:01:56 -0500
  • 2dda7c11a3 More proper fix for the memory issue. comfyanonymous 2024-12-19 16:21:56 -0500
  • 3ad3248ad7 Fix lowvram bug when using a model multiple times in a row. comfyanonymous 2024-12-19 16:04:56 -0500
  • 3b0a3cb6f9 Add unit test for safetensors embedded image previews catboxanon 2024-12-19 15:10:18 -0500
  • b588fdd0f5 Flip minor version check sign. Simon Lui 2024-12-19 10:34:23 -0800
  • 25a3c9e9c3
    added optional "asyncio_loop" argument to allow using existing event loop bigcat88 2024-12-19 19:58:50 +0200
  • 9f6401d8dd Support preview images embedded in safetensors metadata catboxanon 2024-12-19 12:33:19 -0500
  • 51d4abc2cd
    Add support for FORCE_SOFT_EMPTY_CACHE env var to enable cache clearing for AMD GPUs bigcat88 2024-12-19 14:35:29 +0200
  • 7f8d7ae309 Add ImageLabel node and FontManager Gremlation 2024-12-19 19:45:37 +0800
  • 7fa60b6fb8
    Refactor main.py to support external event loop integration Alexander Piskun 2024-12-19 13:44:15 +0200
  • c441048a4f Make VAE Encode tiled node work with video VAE. comfyanonymous 2024-12-19 05:31:39 -0500
  • fdccaa1841 Fix device selector variable name. Simon Lui 2024-12-19 02:12:52 -0800
  • afde678e3c Add oneAPI device selector and some other minor changes. Simon Lui 2024-12-19 01:28:44 -0800
  • caa1c7738d Use raw dir name to serve static web content huchenlei 2024-12-18 16:45:50 -0800
  • 9f4b181ab3 Add fast previews for hunyuan video. v0.3.8 comfyanonymous 2024-12-18 18:24:23 -0500
  • cbbf077593 Small optimizations. comfyanonymous 2024-12-18 18:23:28 -0500
  • 0c04a6ae78
    Add .github folder to maintainer owner list (#6027) Chenlei Hu 2024-12-18 12:06:53 -0800
  • 416ccc9e45
    Update web content to release v1.5.19 (#6105) Chenlei Hu 2024-12-18 12:06:20 -0800
  • 820628ba41 Update web content to release v1.5.19 huchenlei 2024-12-18 12:21:19 -0500
  • fd9ac2bfb8
    Merge branch 'master' into pixart comfyanonymous 2024-12-18 06:39:47 -0500
  • ff2ff02168 Support old diffusion-pipe hunyuan video loras. comfyanonymous 2024-12-18 06:21:29 -0500
  • 4c5c4ddeda Fix regression in VAE code on old pytorch versions. comfyanonymous 2024-12-18 03:08:28 -0500
  • 79badea452 Add ConditioningStableAudio. comfyanonymous 2024-12-18 03:01:12 -0500
  • 37e5390f5f Add: --use-sage-attention to enable SageAttention. comfyanonymous 2024-12-18 01:56:10 -0500
  • 0c853f330c
    Merge branch 'master' into official_repo zhuyu2015 2024-12-18 14:54:59 +0800
  • a4f59bc65e Pick attention implementation based on device in llama code. comfyanonymous 2024-12-18 01:30:20 -0500
  • ca457f7ba1 Properly tokenize the template for hunyuan video. comfyanonymous 2024-12-17 16:18:35 -0500
  • cd6f615038 Fix tiled vae not working with some shapes. comfyanonymous 2024-12-17 09:42:17 -0500
  • 517669aaa3
    add preview 3d node (#6070) Terry Jia 2024-12-17 13:42:24 -0500
  • e4e1bff605 Support diffusion-pipe hunyuan video lora format. comfyanonymous 2024-12-17 07:14:21 -0500
  • d6656b0c0c Support llama hunyuan video text encoder in scaled fp8 format. comfyanonymous 2024-12-17 04:19:22 -0500
  • f4cdedea62 Fix regression with ltxv VAE. comfyanonymous 2024-12-17 02:17:31 -0500
  • 39b1fc4ccc Adjust used dtypes for hunyuan video VAE and diffusion model. comfyanonymous 2024-12-16 23:31:10 -0500
  • d788cbb299
    Merge branch 'comfyanonymous:master' into master Kallen Ding 2024-12-17 10:46:30 +0800
  • 0b25f47bd9 Add some missing imports. comfyanonymous 2024-12-16 19:42:01 -0500
  • 3967c9877e mark 3d nodes as EXPERIMENTAL Terry Jia 2024-12-16 19:39:38 -0500