Commit Graph

  • 2dda7c11a3 More proper fix for the memory issue. comfyanonymous 2024-12-19 16:21:56 -05:00
  • 8b07be7800 Fix lowvram bug when using a model multiple times in a row. comfyanonymous 2024-12-19 16:04:56 -05:00
  • 3ad3248ad7 Fix lowvram bug when using a model multiple times in a row. comfyanonymous 2024-12-19 16:04:56 -05:00
  • 3b0a3cb6f9 Add unit test for safetensors embedded image previews catboxanon 2024-12-19 15:10:18 -05:00
  • b588fdd0f5 Flip minor version check sign. Simon Lui 2024-12-19 10:34:23 -08:00
  • 25a3c9e9c3
    added optional "asyncio_loop" argument to allow using existing event loop bigcat88 2024-12-19 19:58:50 +02:00
  • 9f6401d8dd Support preview images embedded in safetensors metadata catboxanon 2024-12-19 12:33:19 -05:00
  • 51d4abc2cd
    Add support for FORCE_SOFT_EMPTY_CACHE env var to enable cache clearing for AMD GPUs bigcat88 2024-12-19 14:35:29 +02:00
  • 778005af3d
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-19 14:51:33 +03:00
  • 7f8d7ae309 Add ImageLabel node and FontManager Gremlation 2024-12-19 19:45:37 +08:00
  • 7fa60b6fb8
    Refactor main.py to support external event loop integration Alexander Piskun 2024-12-19 13:44:15 +02:00
  • 6eefe6a53b Make VAE Encode tiled node work with video VAE. comfyanonymous 2024-12-19 05:31:39 -05:00
  • c441048a4f Make VAE Encode tiled node work with video VAE. comfyanonymous 2024-12-19 05:31:39 -05:00
  • fdccaa1841 Fix device selector variable name. Simon Lui 2024-12-19 02:12:52 -08:00
  • afde678e3c Add oneAPI device selector and some other minor changes. Simon Lui 2024-12-19 01:28:44 -08:00
  • caa1c7738d Use raw dir name to serve static web content huchenlei 2024-12-18 16:45:50 -08:00
  • 56c023f2fb Add fast previews for hunyuan video. comfyanonymous 2024-12-18 18:24:23 -05:00
  • 9f4b181ab3 Add fast previews for hunyuan video. v0.3.8 comfyanonymous 2024-12-18 18:24:23 -05:00
  • c558cea96a Small optimizations. comfyanonymous 2024-12-18 18:23:28 -05:00
  • cbbf077593 Small optimizations. comfyanonymous 2024-12-18 18:23:28 -05:00
  • 76f5591fb0 Add .github folder to maintainer owner list (#6027) Chenlei Hu 2024-12-18 12:06:53 -08:00
  • 0c04a6ae78
    Add .github folder to maintainer owner list (#6027) Chenlei Hu 2024-12-18 12:06:53 -08:00
  • 8755839453 Update web content to release v1.5.19 (#6105) Chenlei Hu 2024-12-18 12:06:20 -08:00
  • 416ccc9e45
    Update web content to release v1.5.19 (#6105) Chenlei Hu 2024-12-18 12:06:20 -08:00
  • 820628ba41 Update web content to release v1.5.19 huchenlei 2024-12-18 12:21:19 -05:00
  • 43a0204b07
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-18 15:17:15 +03:00
  • fd9ac2bfb8
    Merge branch 'master' into pixart comfyanonymous 2024-12-18 06:39:47 -05:00
  • 9181dbaaa8 Support old diffusion-pipe hunyuan video loras. comfyanonymous 2024-12-18 06:21:29 -05:00
  • ff2ff02168 Support old diffusion-pipe hunyuan video loras. comfyanonymous 2024-12-18 06:21:29 -05:00
  • 947aba46c3
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-18 12:33:32 +03:00
  • 97a136ffa2 Fix regression in VAE code on old pytorch versions. comfyanonymous 2024-12-18 03:08:28 -05:00
  • 4c5c4ddeda Fix regression in VAE code on old pytorch versions. comfyanonymous 2024-12-18 03:08:28 -05:00
  • a46c5f7e28 Add ConditioningStableAudio. comfyanonymous 2024-12-18 03:01:12 -05:00
  • 79badea452 Add ConditioningStableAudio. comfyanonymous 2024-12-18 03:01:12 -05:00
  • c062723ca5
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-18 10:16:43 +03:00
  • 8dc45adbe4 Add: --use-sage-attention to enable SageAttention. comfyanonymous 2024-12-18 01:56:10 -05:00
  • 37e5390f5f Add: --use-sage-attention to enable SageAttention. comfyanonymous 2024-12-18 01:56:10 -05:00
  • 0c853f330c
    Merge branch 'master' into official_repo zhuyu2015 2024-12-18 14:54:59 +08:00
  • fd5d3147dc Pick attention implementation based on device in llama code. comfyanonymous 2024-12-18 01:30:20 -05:00
  • a4f59bc65e Pick attention implementation based on device in llama code. comfyanonymous 2024-12-18 01:30:20 -05:00
  • 0e5fa013b2
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-18 00:43:24 +03:00
  • 5ea21ff2b2 Properly tokenize the template for hunyuan video. comfyanonymous 2024-12-17 16:18:35 -05:00
  • ca457f7ba1 Properly tokenize the template for hunyuan video. comfyanonymous 2024-12-17 16:18:35 -05:00
  • 42a53bfe5a Fix tiled vae not working with some shapes. comfyanonymous 2024-12-17 09:42:17 -05:00
  • cd6f615038 Fix tiled vae not working with some shapes. comfyanonymous 2024-12-17 09:42:17 -05:00
  • 83ad9b0a5f
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-17 22:10:16 +03:00
  • b201130839 add preview 3d node (#6070) Terry Jia 2024-12-17 13:42:24 -05:00
  • 517669aaa3
    add preview 3d node (#6070) Terry Jia 2024-12-17 13:42:24 -05:00
  • 4ace4e9ecb
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-17 19:55:56 +03:00
  • 021ca47559 Support diffusion-pipe hunyuan video lora format. comfyanonymous 2024-12-17 07:14:21 -05:00
  • e4e1bff605 Support diffusion-pipe hunyuan video lora format. comfyanonymous 2024-12-17 07:14:21 -05:00
  • dc574cdc47
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-17 13:57:30 +03:00
  • aa5005ff35 Support llama hunyuan video text encoder in scaled fp8 format. comfyanonymous 2024-12-17 04:19:22 -05:00
  • d6656b0c0c Support llama hunyuan video text encoder in scaled fp8 format. comfyanonymous 2024-12-17 04:19:22 -05:00
  • 4645275c35 Fix regression with ltxv VAE. comfyanonymous 2024-12-17 02:17:31 -05:00
  • f4cdedea62 Fix regression with ltxv VAE. comfyanonymous 2024-12-17 02:17:31 -05:00
  • f642cc115b Adjust used dtypes for hunyuan video VAE and diffusion model. comfyanonymous 2024-12-16 23:31:10 -05:00
  • 39b1fc4ccc Adjust used dtypes for hunyuan video VAE and diffusion model. comfyanonymous 2024-12-16 23:31:10 -05:00
  • d788cbb299
    Merge branch 'comfyanonymous:master' into master Kallen Ding 2024-12-17 10:46:30 +08:00
  • 7fa7a5b733 Add some missing imports. comfyanonymous 2024-12-16 19:42:01 -05:00
  • 0b25f47bd9 Add some missing imports. comfyanonymous 2024-12-16 19:42:01 -05:00
  • 3967c9877e mark 3d nodes as EXPERIMENTAL Terry Jia 2024-12-16 19:39:38 -05:00
  • 2b49852ca2 Basic Hunyuan Video model support. comfyanonymous 2024-12-16 19:35:40 -05:00
  • bda1482a27 Basic Hunyuan Video model support. comfyanonymous 2024-12-16 19:35:40 -05:00
  • f426e83a83 Don't expand mask when not necessary. comfyanonymous 2024-12-16 18:22:50 -05:00
  • 19ee5d9d8b Don't expand mask when not necessary. comfyanonymous 2024-12-16 18:22:50 -05:00
  • ec2ea78501 Add support for attention masking in Flux (#5942) Raphael Walker 2024-12-17 00:21:17 +01:00
  • 61b50720d0
    Add support for attention masking in Flux (#5942) Raphael Walker 2024-12-17 00:21:17 +01:00
  • fcc6dbd342
    Update README.md patientx 2024-12-17 01:56:44 +03:00
  • d42bfc7e1b
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-17 01:56:08 +03:00
  • a567fa77b8
    Update README.md patientx 2024-12-17 01:55:59 +03:00
  • 87d9bdacb1 Update README.md (#6071) Alexander Dyadyun 2024-12-17 03:24:54 +07:00
  • 0f954f34af
    Update README.md (#6071) Alexander Dyadyun 2024-12-17 03:24:54 +07:00
  • 7a27c3c794 Update web content to release v1.5.18 (#6075) Chenlei Hu 2024-12-16 11:38:24 -08:00
  • 5262901c5c
    Update web content to release v1.5.18 (#6075) Chenlei Hu 2024-12-16 11:38:24 -08:00
  • 51451250c1
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-16 22:20:07 +03:00
  • 5a9ad12c8c use String directly to set bg color for load 3d canvas (#6057) Terry Jia 2024-12-16 13:51:40 -05:00
  • cc550d5908
    use String directly to set bg color for load 3d canvas (#6057) Terry Jia 2024-12-16 13:51:40 -05:00
  • 82850ec24f Update web content to release v1.5.18 huchenlei 2024-12-16 11:48:50 -05:00
  • b321bfc8d3 fix mask shapes Raphael Walker 2024-12-16 10:22:12 +01:00
  • b0a56705fd
    Update README.md Alexander Dyadyun 2024-12-16 15:12:13 +07:00
  • 43e79b2113 add preview 3d node Terry Jia 2024-12-15 22:59:49 -05:00
  • d708e74d89
    Update README.md for Intel GPUs Qiacheng Li 2024-12-15 16:43:20 -08:00
  • 5e87263dc9
    Update README.md Qiacheng Li 2024-12-15 16:37:23 -08:00
  • cf60f9c907
    Update README.md Qiacheng Li 2024-12-15 16:17:10 -08:00
  • 4109d3f831
    Update README.md Qiacheng Li 2024-12-15 15:33:56 -08:00
  • 1731ce0ea5
    Update README.md for Intel GPU Qiacheng Li 2024-12-15 15:19:41 -08:00
  • 37d171a3a5
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-15 18:15:51 +03:00
  • 354a73c663
    Merge pull request #50 from Lolen10/master patientx 2024-12-15 18:15:42 +03:00
  • 3e3ac38c11
    Update README.md Lolen10 2024-12-15 13:43:42 +00:00
  • 07c0e793b9 Fix case of ExecutionBlocker not handled correctly with INPUT_IS_LIST. comfyanonymous 2024-12-15 08:41:35 -05:00
  • 6d1a3f7d00 Fix case of ExecutionBlocker not handled correctly with INPUT_IS_LIST. comfyanonymous 2024-12-15 08:41:35 -05:00
  • 477e5d1c0b
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-15 15:29:17 +03:00
  • 1c6a208891 (fix): added "model_type" to photomaker node (#6047) Alexander Piskun 2024-12-15 08:18:02 +03:00
  • 1b3a650f19
    (fix): added "model_type" to photomaker node (#6047) Alexander Piskun 2024-12-15 08:18:02 +03:00
  • 81404ce423 use String directly to set bg color for load 3d canvas Terry Jia 2024-12-14 22:01:49 -05:00
  • 07ad1c7ee1 Use same detection key logic for PixArt diffusers City 2024-12-14 23:48:35 +01:00
  • 703b79b99d PixArtAlpha text encode with conds City 2024-12-14 23:09:04 +01:00
  • 41b7be08dc Fix aspect ratio logic City 2024-12-14 23:06:02 +01:00
  • 51dded3398 Basic PixArt LoRA support City 2024-12-14 22:35:32 +01:00