Commit Graph

  • 4f7a3cb6fb unet -> diffusion_models. comfyanonymous 2024-08-17 21:28:36 -04:00
  • bb222ceddb Fix loras having a weak effect when applied on fp8. comfyanonymous 2024-08-17 14:07:19 -04:00
  • 14af129c55 Improve execution UX. comfyanonymous 2024-08-17 11:36:10 -04:00
  • fca42836f2 Add model_options for text encoder. comfyanonymous 2024-08-17 10:15:13 -04:00
  • 858d51f91a Fix VAEDecode -> Preview not being executed first. comfyanonymous 2024-08-17 04:08:54 -04:00
  • cd5017c1c9 calculate_weight function to use a different dtype. comfyanonymous 2024-08-17 01:06:08 -04:00
  • 83f343146a Fix potential lowvram issue. comfyanonymous 2024-08-16 17:12:42 -04:00
  • b021cf67c7 Update frontend to 1.2.26 (#4415) Chenlei Hu 2024-08-16 15:25:02 -04:00
  • 1770fc77ed Implement support for taef1 latent previews (#4409) Matthew Turnshek 2024-08-16 12:53:13 -04:00
  • 05a9f3faa1 Log a warning when there's an issue with IS_CHANGED. comfyanonymous 2024-08-16 08:50:17 -04:00
  • 86c5970ac0 Fix custom nodes hooking the map_node_over_list and breaking things. comfyanonymous 2024-08-16 08:40:31 -04:00
  • bfc214f434 Use new TS frontend uncompressed (#4379) Chenlei Hu 2024-08-15 16:50:25 -04:00
  • 3f5939add6 Tell github not to count the web directory in language stats. comfyanonymous 2024-08-15 13:48:18 -04:00
  • 5960f946a9 Move a few files from comfy -> comfy_execution. comfyanonymous 2024-08-15 09:37:30 -04:00
  • 5cfe38f41c Execution Model Inversion (#2666) guill 2024-08-15 08:21:11 -07:00
  • 0f9c2a7822 Try to fix SDXL OOM issue on some configurations. comfyanonymous 2024-08-14 23:08:54 -04:00
  • 153d0a8142 Add a update/update_comfyui_stable.bat to the standalones. comfyanonymous 2024-08-14 22:29:23 -04:00
  • ab4dd19b91 Remove legacy ui test files (#4316) Chenlei Hu 2024-08-14 21:01:06 -04:00
  • f1d6cef71c Revert "Disable cuda malloc by default." comfyanonymous 2024-08-14 08:38:07 -04:00
  • 33fb282d5c Fix issue. comfyanonymous 2024-08-14 02:51:47 -04:00
  • 50bf66e5c4 Disable cuda malloc by default. comfyanonymous 2024-08-14 02:49:25 -04:00
  • e60e19b175 Add support for simple tooltips (#3842) pythongosssss 2024-08-14 06:22:10 +01:00
  • a5af64d3ce Revert "Not sure if this actually changes anything but it can't hurt." comfyanonymous 2024-08-14 01:05:17 -04:00
  • 3e52e0364c Add model downloading endpoint. (#4248) Robin Huang 2024-08-13 12:48:52 -07:00
  • 34608de2e9 Not sure if this actually changes anything but it can't hurt. comfyanonymous 2024-08-13 12:35:25 -04:00
  • 39fb74c5bd Fix bug when model cannot be partially unloaded. v0.0.8 comfyanonymous 2024-08-13 03:57:55 -04:00
  • 74e124f4d7 Fix some issues with TE being in lowvram mode. comfyanonymous 2024-08-12 23:42:21 -04:00
  • a562c17e8a load_unet -> load_diffusion_model with a model_options argument. comfyanonymous 2024-08-12 23:18:54 -04:00
  • 5942c17d55 Order of operations matters. comfyanonymous 2024-08-12 21:56:18 -04:00
  • c032b11e07 xlabs Flux controlnet implementation. (#4260) comfyanonymous 2024-08-12 21:22:22 -04:00
  • b8ffb2937f Memory tweaks. v0.0.7 comfyanonymous 2024-08-12 15:03:33 -04:00
  • ce37c11164 add DS_Store to gitignore (#4324) Vladimir Semyonov 2024-08-12 19:32:34 +03:00
  • b5c3906b38 Automatically link the Comfy CI page on PRs (#4326) Alex "mcmonkey" Goodwin 2024-08-12 09:32:16 -07:00
  • 5d43e75e5b Fix some issues with the model sometimes not getting patched. comfyanonymous 2024-08-12 12:27:54 -04:00
  • 517f4a94e4 Fix some lora loading slowdowns. comfyanonymous 2024-08-12 11:38:06 -04:00
  • 52a471c5c7 Change name of log. comfyanonymous 2024-08-12 10:35:06 -04:00
  • ad76574cb8 Fix some potential issues with the previous commits. comfyanonymous 2024-08-12 00:23:29 -04:00
  • 9acfe4df41 Support loading directly to vram with CLIPLoader node. comfyanonymous 2024-08-12 00:06:01 -04:00
  • 9829b013ea Fix mistake in last commit. comfyanonymous 2024-08-12 00:00:17 -04:00
  • 5c69cde037 Load TE model straight to vram if certain conditions are met. comfyanonymous 2024-08-11 23:50:01 -04:00
  • e9589d6d92 Add a way to set model dtype and ops from load_checkpoint_guess_config. comfyanonymous 2024-08-11 08:50:34 -04:00
  • 0d82a798a5 Remove the ckpt_path from load_state_dict_guess_config. comfyanonymous 2024-08-11 08:37:35 -04:00
  • 925fff26fd alternative to load_checkpoint_guess_config that accepts a loaded state dict (#4249) ljleb 2024-08-11 08:36:52 -04:00
  • 75b9b55b22 Fix issues with #4302 and support loading diffusers format flux. v0.0.6 comfyanonymous 2024-08-10 21:28:24 -04:00
  • 1765f1c60c FLUX: Added full diffusers mapping for FLUX.1 schnell and dev. Adds full LoRA support from diffusers LoRAs. (#4302) Jaret Burkett 2024-08-10 19:26:41 -06:00
  • 1de69fe4d5 Fix some issues with inference slowing down. comfyanonymous 2024-08-10 15:29:36 -04:00
  • ae197f651b Speed up hunyuan dit inference a bit. comfyanonymous 2024-08-10 07:36:27 -04:00
  • 1b5b8ca81a Fix regression. v0.0.5 comfyanonymous 2024-08-09 21:45:21 -04:00
  • 6678d5cf65 Fix regression. comfyanonymous 2024-08-09 14:02:38 -04:00
  • e172564eea Update controlnet.py to fix the default controlnet weight as constant (#4285) TTPlanetPig 2024-08-10 01:40:05 +08:00
  • a3cc326748 Better fix for lowvram issue. comfyanonymous 2024-08-09 12:16:25 -04:00
  • 86a97e91fc Fix controlnet regression. comfyanonymous 2024-08-09 12:08:58 -04:00
  • 5acdadc9f3 Fix issue with some lowvram weights. comfyanonymous 2024-08-09 03:58:28 -04:00
  • 55ad9d5f8c Fix regression. comfyanonymous 2024-08-09 03:36:40 -04:00
  • a9f04edc58 Implement text encoder part of HunyuanDiT loras. comfyanonymous 2024-08-09 03:21:10 -04:00
  • a475ec2300 Cleanup HunyuanDit controlnets. comfyanonymous 2024-08-09 02:35:19 -04:00
  • 06eb9fb426 feat: add support for HunYuanDit ControlNet (#4245) 来新璐 2024-08-09 14:59:24 +08:00
  • 413322645e Raw torch is faster than einops? comfyanonymous 2024-08-08 22:09:29 -04:00
  • 11200de970 Cleaner code. comfyanonymous 2024-08-08 20:07:09 -04:00
  • 037c38eb0f Try to improve inference speed on some machines. comfyanonymous 2024-08-08 17:28:35 -04:00
  • 1e11d2d1f5 Better prints. comfyanonymous 2024-08-08 17:05:16 -04:00
  • 65ea6be38f PullRequest CI Run: use pull_request_target to allow the CI Dashboard to work (#4277) Alex "mcmonkey" Goodwin 2024-08-08 14:20:48 -07:00
  • 5df6f57b5d minor fix on copypasta action name (#4276) Alex "mcmonkey" Goodwin 2024-08-08 13:30:59 -07:00
  • 6588bfdef9 add GitHub workflow for CI tests of PRs (#4275) Alex "mcmonkey" Goodwin 2024-08-08 13:24:49 -07:00
  • 50ed2879ef Add full CI test matrix GitHub Workflow (#4274) Alex "mcmonkey" Goodwin 2024-08-08 12:40:07 -07:00
  • 66d4233210 Fix. comfyanonymous 2024-08-08 15:16:51 -04:00
  • 591010b7ef Support diffusers text attention flux loras. comfyanonymous 2024-08-08 14:45:52 -04:00
  • 08f92d55e9 Partial model shift support. comfyanonymous 2024-08-08 03:27:37 -04:00
  • 8115d8cce9 Add Flux fp16 support hack. comfyanonymous 2024-08-07 15:08:39 -04:00
  • 6969fc9ba4 Make supported_dtypes a priority list. comfyanonymous 2024-08-07 15:00:06 -04:00
  • cb7c4b4be3 Workaround for lora OOM on lowvram mode. comfyanonymous 2024-08-07 14:30:54 -04:00
  • 1208863eca Fix "Comfy" lora keys. comfyanonymous 2024-08-07 13:49:31 -04:00
  • e1c528196e Fix bundled embed. comfyanonymous 2024-08-07 13:30:45 -04:00
  • 17030fd4c0 Support for "Comfy" lora format. comfyanonymous 2024-08-07 13:18:32 -04:00
  • c19dcd362f Controlnet code refactor. comfyanonymous 2024-08-07 12:59:28 -04:00
  • 1c08bf35b4 Support format for embeddings bundled in loras. comfyanonymous 2024-08-07 03:45:25 -04:00
  • 2a02546e20 Add type hints to folder_paths.py (#4191) PhilWun 2024-08-07 03:59:34 +02:00
  • b334605a66 Fix OOMs happening in some cases. v0.0.4 comfyanonymous 2024-08-06 13:27:48 -04:00
  • de17a9755e Unload all models if there's an OOM error. comfyanonymous 2024-08-06 03:30:28 -04:00
  • c14ac98fed Unload models and load them back in lowvram mode no free vram. comfyanonymous 2024-08-06 03:22:39 -04:00
  • 2894511893 Clone taesd with depth of 1 to reduce download size. (#4232) Robin Huang 2024-08-05 22:46:09 -07:00
  • f3bc40223a Add format metadata to CLIP save to make compatible with diffusers safetensors loading (#4233) Silver 2024-08-06 07:45:24 +02:00
  • 841e74ac40 Change browser test CI python to 3.8 (#4234) Chenlei Hu 2024-08-06 01:27:28 -04:00
  • 2d75df45e6 Flux tweak memory usage. comfyanonymous 2024-08-05 21:58:28 -04:00
  • 1abc9c8703 Stable release uses cached dependencies (#4231) Robin Huang 2024-08-05 17:07:16 -07:00
  • 8edbcf5209 Improve performance on some lowend GPUs. comfyanonymous 2024-08-05 16:24:04 -04:00
  • e545a636ba This probably doesn't work anymore. comfyanonymous 2024-08-05 12:31:12 -04:00
  • 33e5203a2a Don't cache index.html (#4211) bymyself 2024-08-05 09:25:28 -07:00
  • a178e25912 Fix Flux FP64 math on XPU (#4210) a-One-Fan 2024-08-05 08:26:20 +03:00
  • 78e133d041 Support simple diffusers Flux loras. comfyanonymous 2024-08-04 21:59:42 -04:00
  • 7afa985fba Correct spelling 'token_weight_pars_t5' to 'token_weight_pairs_t5' (#4200) Silver 2024-08-04 23:10:02 +02:00
  • ddb6a9f47c Set the step in EmptySD3LatentImage to 16. comfyanonymous 2024-08-04 15:59:02 -04:00
  • 3b71f84b50 ONNX tracing fixes. comfyanonymous 2024-08-04 15:45:43 -04:00
  • 0a6b008117 Fix issue with some custom nodes. comfyanonymous 2024-08-04 10:03:33 -04:00
  • 56f3c660bf ModelSamplingFlux now takes a resolution and adjusts the shift with it. comfyanonymous 2024-08-04 04:06:00 -04:00
  • f7a5107784 Fix crash. comfyanonymous 2024-08-03 16:55:38 -04:00
  • 91be9c2867 Tweak lowvram memory formula. comfyanonymous 2024-08-03 16:34:27 -04:00
  • 03c5018c98 Lower lowvram memory to 1/3 of free memory. comfyanonymous 2024-08-03 15:14:07 -04:00
  • 2ba5cc8b86 Fix some issues. comfyanonymous 2024-08-03 15:06:40 -04:00
  • 1e68002b87 Cap lowvram to half of free memory. comfyanonymous 2024-08-03 14:50:20 -04:00