Commit Graph

  • d9c5f38fa7 Make fast fp8 take a bit less peak memory. comfyanonymous 2024-12-24 18:05:19 -05:00
  • 99a1fb6027 Make fast fp8 take a bit less peak memory. comfyanonymous 2024-12-24 18:05:19 -05:00
  • b0d8059f9f
    Update main.py Lucas - BLOCK33 2024-12-24 18:56:41 -03:00
  • 1d3e8377e6 modified: main.py tonynoce 2024-12-24 16:57:11 -03:00
  • 7be71a8142 Rename kl_optimal_schedule to kl_optimal_scheduler to be more consistent blepping 2024-12-24 10:50:08 -07:00
  • 2992402051 Add kl_optimal scheduler blepping 2024-12-24 10:08:09 -07:00
  • 1741ad55ac
    added ability to specify custom "prompt_id" bigcat88 2024-12-24 18:54:43 +02:00
  • 1f6ab7dbfb
    support for "unload_models" flag when creating a task bigcat88 2024-12-24 17:41:49 +02:00
  • 077ebf7b17
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-24 16:53:56 +03:00
  • 63ad2323f1 Prevent black images in VAE Decode (Tiled) node. comfyanonymous 2024-12-24 07:36:30 -05:00
  • 73e04987f7 Prevent black images in VAE Decode (Tiled) node. comfyanonymous 2024-12-24 07:36:30 -05:00
  • c20a09c82f Add temporal tiling to VAE Encode (Tiled) node. comfyanonymous 2024-12-24 07:10:09 -05:00
  • 5388df784a Add temporal tiling to VAE Encode (Tiled) node. comfyanonymous 2024-12-24 07:10:09 -05:00
  • 0f7b4f063d
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-24 15:06:02 +03:00
  • f9acbccf0a Enable External Event Loop Integration for ComfyUI [refactor] (#6114) Alexander Piskun 2024-12-24 14:38:52 +03:00
  • 26e0ba8f8c
    Enable External Event Loop Integration for ComfyUI [refactor] (#6114) Alexander Piskun 2024-12-24 14:38:52 +03:00
  • 0e9e3f4e6b
    Merge efa53c9e928f5d693ef4b75ebbc95cff8f2af6c1 into bc6dac4327a838f8583f6272cc3cc612b9b16134 Alex "mcmonkey" Goodwin 2024-12-24 11:37:10 +08:00
  • 9946fff072 Add temporal tiling to VAE Decode (Tiled) node. comfyanonymous 2024-12-23 20:03:37 -05:00
  • bc6dac4327 Add temporal tiling to VAE Decode (Tiled) node. comfyanonymous 2024-12-23 20:03:37 -05:00
  • 547eb21d06 serve workflow templates from custom_nodes bezo97 2024-12-23 23:51:24 +01:00
  • ce5afecc36
    Only use events for devices supporting nonblocking Austin Mroz 2024-12-23 16:43:43 -06:00
  • b6e3bc2451 add GET /workflow_templates bezo97 2024-12-23 20:15:51 +01:00
  • 711d5b09c6 Attempt to fix hooks being disabled at first step of second sampler catboxanon 2024-12-23 12:45:56 -05:00
  • 00afa8b34f
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-23 11:36:49 +03:00
  • 21e330a8d8 Use raw dir name to serve static web content (#6107) Chenlei Hu 2024-12-23 03:29:42 -05:00
  • f18ebbd316
    Use raw dir name to serve static web content (#6107) Chenlei Hu 2024-12-23 03:29:42 -05:00
  • 6b963ebdc5 Add a try except block so if torch version is weird it won't crash. comfyanonymous 2024-12-23 03:22:48 -05:00
  • 15564688ed Add a try except block so if torch version is weird it won't crash. comfyanonymous 2024-12-23 03:22:48 -05:00
  • 21f20638bd move code to model_lora_keys_unet rickard 2024-12-23 09:20:22 +01:00
  • 668cc89307 Add oneAPI device selector for xpu and some other changes. (#6112) Simon Lui 2024-12-23 00:18:32 -08:00
  • c6b9c11ef6
    Add oneAPI device selector for xpu and some other changes. (#6112) Simon Lui 2024-12-23 00:18:32 -08:00
  • 403a081215
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-23 10:33:06 +03:00
  • 31b6852f19 load ltx loras trained with finetrainers rickard 2024-12-23 08:19:34 +01:00
  • e7747a1e35 Make --novram completely offload weights. comfyanonymous 2024-12-23 01:50:11 -05:00
  • e44d0ac7f7 Make --novram completely offload weights. comfyanonymous 2024-12-23 01:50:11 -05:00
  • f1edcbd074 Comment out some useless code. comfyanonymous 2024-12-22 23:51:14 -05:00
  • 56bc64f351 Comment out some useless code. comfyanonymous 2024-12-22 23:51:14 -05:00
  • 69518a310f fixed a bug in ldm/pixart/blocks.py (#6158) zhangp365 2024-12-23 12:44:20 +08:00
  • f7d83b72e0
    fixed a bug in ldm/pixart/blocks.py (#6158) zhangp365 2024-12-23 12:44:20 +08:00
  • e440136a18 Fix lowvram issue with ltxv vae. comfyanonymous 2024-12-22 23:20:17 -05:00
  • 80f07952d2 Fix lowvram issue with ltxv vae. comfyanonymous 2024-12-22 23:20:17 -05:00
  • 757335d901
    Update supported_models.py patientx 2024-12-23 02:54:49 +03:00
  • 713eca2176
    Update supported_models.py patientx 2024-12-23 02:32:50 +03:00
  • e9d8cad2f0
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-22 16:56:29 +03:00
  • ccdd4a64ea
    fixed a bug in ldm/pixart/blocks.py zhangp365 2024-12-22 20:20:48 +08:00
  • 12f0beabf0 Relax minimum ratio of weights loaded in memory on nvidia. comfyanonymous 2024-12-22 03:06:37 -05:00
  • 57f330caf9 Relax minimum ratio of weights loaded in memory on nvidia. comfyanonymous 2024-12-22 03:06:37 -05:00
  • f5a2795bbc
    Update README.md patientx 2024-12-21 23:04:40 +03:00
  • 6b20fd5de4
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-21 23:04:07 +03:00
  • db9efe3c20
    Update README.md patientx 2024-12-21 23:04:01 +03:00
  • e023ab9d80 Add that Hunyuan Video and Pixart are supported to readme. comfyanonymous 2024-12-21 11:31:39 -05:00
  • 601ff9e3db Add that Hunyuan Video and Pixart are supported to readme. comfyanonymous 2024-12-21 11:31:39 -05:00
  • 85b05078aa remove minimum step count for AYS (#6137) TechnoByte 2024-12-21 16:05:09 +01:00
  • 341667c4d5
    remove minimum step count for AYS (#6137) TechnoByte 2024-12-21 16:05:09 +01:00
  • 819e120348
    Update README.md patientx 2024-12-21 15:52:58 +03:00
  • 88ae56dcf9
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-21 15:52:28 +03:00
  • 68f7b148ee
    Update README.md patientx 2024-12-21 15:52:21 +03:00
  • 813b8df872
    Fix race condition in preview code. Austin Mroz 2024-12-19 13:17:00 -06:00
  • 228704b77c chore(pyproject): Add pyproject.toml for Custom Node Registry snomiao 2024-12-21 02:23:04 +00:00
  • 5d8a211e84 chore(publish): Add Github Action for Publishing to Comfy Registry snomiao 2024-12-21 02:23:03 +00:00
  • 160c4e2335 Update README.md for Intel GPUs (#6069) Qiacheng Li 2024-12-20 15:04:03 -08:00
  • 1419dee915
    Update README.md for Intel GPUs (#6069) Qiacheng Li 2024-12-20 15:04:03 -08:00
  • b38caef86c Get rid of meshgrid warning. comfyanonymous 2024-12-20 18:02:12 -05:00
  • da13b6b827 Get rid of meshgrid warning. comfyanonymous 2024-12-20 18:02:12 -05:00
  • 03e2a443b2 Remove useless code. comfyanonymous 2024-12-20 17:50:03 -05:00
  • c86cd58573 Remove useless code. comfyanonymous 2024-12-20 17:50:03 -05:00
  • 058c9d8df0 Remove some useless code. comfyanonymous 2024-12-20 17:43:50 -05:00
  • b5fe39211a Remove some useless code. comfyanonymous 2024-12-20 17:43:50 -05:00
  • 4d64ade41f
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-21 01:30:32 +03:00
  • 1dc3f45101 Some fixes/cleanups to pixart code. comfyanonymous 2024-12-20 17:10:52 -05:00
  • e946667216 Some fixes/cleanups to pixart code. comfyanonymous 2024-12-20 17:10:52 -05:00
  • 37fc9a3ff2
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-21 00:37:40 +03:00
  • 895e78edc3 Undo changes to README.md. Simon Lui 2024-12-20 13:30:09 -08:00
  • 917717a0a4 Replace print with logging (#6138) Chenlei Hu 2024-12-20 13:24:55 -08:00
  • d7969cb070
    Replace print with logging (#6138) Chenlei Hu 2024-12-20 13:24:55 -08:00
  • e8274e9304 nit huchenlei 2024-12-20 12:50:46 -08:00
  • 62905871cc nit huchenlei 2024-12-20 12:46:24 -08:00
  • 8dfda4f6c8 nit huchenlei 2024-12-20 12:44:56 -08:00
  • 923c5ca8de nit huchenlei 2024-12-20 09:51:03 -08:00
  • d7da99a138 nit huchenlei 2024-12-20 09:50:05 -08:00
  • 678ac2ffc9 nit huchenlei 2024-12-20 09:48:57 -08:00
  • b356655340 Replace print with logging huchenlei 2024-12-20 09:46:20 -08:00
  • a3a893abeb Add PixArt model support (#6055) City 2024-12-20 21:25:00 +01:00
  • bddb02660c
    Add PixArt model support (#6055) City 2024-12-20 21:25:00 +01:00
  • ca9b1b18e6
    Update symmetric_patchifier.py Miklos Nagy 2024-12-20 19:29:20 +01:00
  • 09853b5e6e
    remove minimum step count for AYS TechnoByte 2024-12-20 18:36:17 +01:00
  • 07ea41ecc1
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-20 13:06:18 +03:00
  • de547c1399 Support new LTXV VAE. comfyanonymous 2024-12-20 04:38:29 -05:00
  • 418eb7062d Support new LTXV VAE. v0.3.9 comfyanonymous 2024-12-20 04:38:29 -05:00
  • 7b3a99adc6
    Update README.md patientx 2024-12-20 10:57:06 +03:00
  • b5e72b093b
    added reserve-vram for better memory management for low mem amd gpu's. patientx 2024-12-20 10:54:05 +03:00
  • d6edc2c53c
    refactor: moved logic of "post_prompt" endpoint to sub-function bigcat88 2024-12-20 09:41:28 +02:00
  • ebf13dfe56
    Merge branch 'comfyanonymous:master' into master patientx 2024-12-20 10:05:56 +03:00
  • f4902ea0d4 Fix some more video tiled encode issues. comfyanonymous 2024-12-19 23:14:03 -05:00
  • cac68ca813 Fix some more video tiled encode issues. comfyanonymous 2024-12-19 23:14:03 -05:00
  • 2c10a7611b Fix tiled hunyuan video VAE encode issue. comfyanonymous 2024-12-19 22:52:37 -05:00
  • 52c1d933b2 Fix tiled hunyuan video VAE encode issue. comfyanonymous 2024-12-19 22:52:37 -05:00
  • bfd792e8b0 Support preview images embedded in safetensors metadata (#6119) catboxanon 2024-12-19 17:01:56 -05:00
  • 3cacd3fca5
    Support preview images embedded in safetensors metadata (#6119) catboxanon 2024-12-19 17:01:56 -05:00
  • 7225891b48 More proper fix for the memory issue. comfyanonymous 2024-12-19 16:21:56 -05:00