Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• e9e9a031a8 Show a better error when the workflow OOMs. (#8574) comfyanonymous 2025-06-18 03:55:21 -07:00
• d7430c529a Update frontend to 1.22.2 (#8567) filtered 2025-06-17 15:58:28 -07:00
• cd88f709ab Update template version (#8563) ComfyUI Wiki 2025-06-17 19:11:59 +08:00
• 4459a17e82 Add Cosmos Predict2 to README. (#8562) comfyanonymous 2025-06-17 02:18:01 -07:00
• 483b3e62e0 ComfyUI version v0.3.41 comfyanonymous 2025-06-16 23:34:46 -04:00
• 8e81c507d2 Multistep DPM++ SDE samplers for RF (#8541) chaObserv 2025-06-17 02:47:10 +08:00
• e1c6dc720e Allow setting min_length with tokenizer_data. (#8547) comfyanonymous 2025-06-16 10:43:52 -07:00
• 7ea79ebb9d Add correct eps to ltxv rmsnorm. (#8542) comfyanonymous 2025-06-15 09:21:25 -07:00
• ae75a084df SaveLora now saves in the same filename format as all the other nodes. (#8538) comfyanonymous 2025-06-15 00:44:59 -07:00
• d6a2137fc3 Support Cosmos predict2 image to video models. (#8535) comfyanonymous 2025-06-14 18:37:07 -07:00
• 53e8d8193c Generalize SEEDS samplers (#8529) chaObserv 2025-06-15 04:58:16 +08:00
• 29596bd53f Small cosmos attention code refactor. (#8530) comfyanonymous 2025-06-14 02:02:05 -07:00
• 803af1e0c3 allow extra settings from pyproject.toml (#8526) Terry Jia 2025-06-13 23:11:55 -04:00
• 6673939e76 Bump template to 0.1.28 (#8510) ComfyUI Wiki 2025-06-14 11:11:00 +08:00
• f74778e75d Bump embedded docs to 0.2.2 (#8512) ComfyUI Wiki 2025-06-14 11:06:28 +08:00
• 520eb77b72 LoRA Trainer: LoRA training node in weight adapter scheme (#8446) Kohaku-Blueleaf 2025-06-14 07:25:59 +08:00
• 5bf69bde35 Add cosmos_rflow option to ModelSamplingContinuousEDM node. (#8523) comfyanonymous 2025-06-13 14:47:52 -07:00
• c69af655aa Uncap cosmos predict2 res and fix mem estimation. (#8518) comfyanonymous 2025-06-13 04:30:18 -07:00
• 251f54a2ad Basic initial support for cosmos predict2 text to image 2B and 14B models. (#8517) comfyanonymous 2025-06-13 04:05:23 -07:00
• c6529c0d77 don't validate string inputs with VALIDATE_INPUTS (#8508) Christian Byrne 2025-06-12 17:17:10 -07:00
• baa8c8cdd3 Add '@prerelease' to use latest test frontend (#8501) filtered 2025-06-12 17:03:27 -07:00
• 40fd39c7cb debug -> warning (#8506) comfyanonymous 2025-06-12 14:14:59 -07:00
• 4d1c4b9797 Auto register web folder (#8505) Terry Jia 2025-06-12 16:24:39 -04:00
• d2566eb4b2 Add a warning for old python versions. (#8504) comfyanonymous 2025-06-12 12:38:33 -07:00
• ef7e885fe4 Revert "Update requirements.txt (#8487)" (#8502) filtered 2025-06-12 11:10:48 -07:00
• ecb8d15e7a Allow specifying any frontend semver suffixes (#8498) filtered 2025-06-11 18:41:30 -07:00
• 365f9ed157 Revert "auto register web folder from pyproject (#8478)" (#8497) comfyanonymous 2025-06-11 14:28:04 -07:00
• 50c605e957 Add support for sqlite database (#8444) pythongosssss 2025-06-11 21:43:39 +01:00
• 9685d4f3c3 auto register web folder from pyproject (#8478) Terry Jia 2025-06-11 16:21:28 -04:00
• 8a4ff747bd Fix mistake in last commit. (#8496) comfyanonymous 2025-06-11 12:13:29 -07:00
• af1eb58be8 Fix black images on some flux models in fp16. (#8495) comfyanonymous 2025-06-11 12:09:11 -07:00
• 373a9386a4 Update requirements.txt (#8487) ComfyUI Wiki 2025-06-11 17:10:46 +08:00
• 6e28a46454 Apple most likely is never fixing the fp16 attention bug. (#8485) comfyanonymous 2025-06-10 10:06:24 -07:00
• c7b25784b1 Fix WebcamCapture IS_CHANGED signature (#8413) Kent Mewhort 2025-06-09 13:05:54 -04:00
• 7f800d04fa Enable AMD fp8 and pytorch attention on some GPUs. (#8474) comfyanonymous 2025-06-09 09:50:39 -07:00
• 97755eed46 Enable fp8 ops by default on gfx1201 (#8464) comfyanonymous 2025-06-08 11:15:34 -07:00
• daf9d25ee2 Cleaner torch version comparisons. (#8453) comfyanonymous 2025-06-07 07:01:15 -07:00
• 3b4b171e18 Alternate fix for #8435 (#8442) comfyanonymous 2025-06-06 06:43:27 -07:00
• d8759c772b Update README.md (#8427) Olexandr88 2025-06-05 20:44:29 +03:00
• 4248b1618f Let chroma TE work on regular flux. (#8429) comfyanonymous 2025-06-05 07:07:17 -07:00
• 866f6cdab4 ComfyUI version 0.3.40 comfyanonymous 2025-06-04 22:18:54 -04:00
• 3aa83feeec [refactor] remove version prefixes from Ideogram node categories (#8418) Christian Byrne 2025-06-04 18:56:38 -07:00
• 871749c208 Add batch to GetImageSize node. (#8419) comfyanonymous 2025-06-04 06:40:21 -07:00
• fcc1643c52 Sub call to deprecated pillow API Image.ANTIALIAS (#8415) SD 2025-06-04 18:33:42 +05:30
• 20687293fe Update frontend to 1.21.7 (#8410) filtered 2025-06-04 05:57:13 -07:00
• 47d55b8b45 add support to read pyproject.toml from custom node (#8357) Terry Jia 2025-06-03 19:59:13 -04:00
• 310f4b6ef8 Add api nodes to readme. (#8402) comfyanonymous 2025-06-03 01:26:44 -07:00
• 856448060c [feat] Add GetImageSize node (#8386) Christian Byrne 2025-06-02 18:57:50 -07:00
• 312d511630 Style fix. (#8390) comfyanonymous 2025-06-02 04:22:02 -07:00
• 4f4f1c642a Update fix for potential XSS on /view (#8384) Jesse Gonyou 2025-06-02 06:52:44 -04:00
• 010954d277 [BugFix] Update frontend to 1.21.6 (#8383) filtered 2025-06-02 14:57:44 +10:00
• 6d46bb4b4c [BugFix] Update frontend to 1.21.5 (#8382) filtered 2025-06-02 06:47:14 +10:00
• 67f57c5bcc [feat] add custom node testing requirement to issue templates (#8374) Christian Byrne 2025-06-01 12:47:07 -07:00
• fd943c928f [BugFix] Update frontend to 1.21.4 (#8377) filtered 2025-06-02 03:57:53 +10:00
• d3bd983b91 Bump template to 0.1.25 (#8372) ComfyUI Wiki 2025-06-01 17:41:17 +08:00
• fb4754624d Make the casting in lists the same as regular inputs. (#8373) comfyanonymous 2025-06-01 02:39:54 -07:00
• 180db6753f Add Help Menu in NodeLibrarySidebarTab (#8179) Benjamin Lu 2025-06-01 04:32:32 -04:00
• d062fcc5c0 [feat] Add ImageStitch node for concatenating images (#8369) Christian Byrne 2025-06-01 01:28:52 -07:00
• 456abad834 Update frontend to 1.21 (#8366) filtered 2025-06-01 15:10:04 +10:00
• 19e45e9b0e Make it easier to pass lists of tensors to models. (#8358) comfyanonymous 2025-05-31 17:00:20 -07:00
• 97f23b81f3 Bump template to 0.1.23 (#8353) ComfyUI Wiki 2025-05-31 14:05:42 +08:00
• 08b7cc7506 use fused multiply-add pointwise ops in chroma (#8279) drhead 2025-05-30 18:09:54 -04:00
• 6c319cbb4e fix: custom comfy-api-base works with subpath (#8332) BennyKok 2025-05-31 05:51:28 +08:00
• df1aebe52e Remove huchenlei from CODEOWNERS (#8350) Chenlei Hu 2025-05-30 17:27:52 -04:00
• 704fc78854 Put ROCm version in tuple to make it easier to enable stuff based on it. (#8348) comfyanonymous 2025-05-30 12:41:02 -07:00
• 1d9fee79fd Add node for regex replace(sub) operation (#8340) JettHu 2025-05-31 03:08:59 +08:00
• aeba0b3a26 Reduce code duplication for [pro] and [max], rename Pro and Max to [pro] and [max] to be consistent with other BFL nodes, make default seed for Kontext nodes be 1234. since 0 is interpreted by API as 'choose random seed' (#8337) Jedrzej Kosinski 2025-05-29 14:14:27 -07:00
• 094306b626 ComfyUI version 0.3.39 comfyanonymous 2025-05-29 14:26:39 -04:00
• 31260f0275 Update templates 0.1.22 (#8334) filtered 2025-05-30 03:52:27 +10:00
• f1c9ca816a Add BFL Kontext API Nodes. (#8333) Robin Huang 2025-05-29 10:27:40 -07:00
• f2289a1f59 Delete useless file. (#8327) comfyanonymous 2025-05-29 05:29:37 -07:00
• fb83eda287 Revert "Add support for Veo3 API node." (#8322) Robin Huang 2025-05-29 00:03:11 -07:00
• 5e5e46d40c Not really tested WAN Phantom Support. (#8321) comfyanonymous 2025-05-28 20:46:15 -07:00
• 4eba3161cf Refactor Pika API node imports and fix unique_id issue. (#8319) Yoland Yan 2025-05-28 20:42:25 -07:00
• 592d056100 Add support for Veo3 API node. (#8320) Robin Huang 2025-05-28 20:42:02 -07:00
• 1c1687ab1c Support HiDream SimpleTuner loras. (#8318) comfyanonymous 2025-05-28 15:47:15 -07:00
• e6609dacde ComfyUI version 0.3.38 comfyanonymous 2025-05-28 02:15:11 -04:00
• ba37e67964 update frontend patch 1.20.7 (#8312) Christian Byrne 2025-05-27 22:42:18 -07:00
• 06c661004e Memory estimation code can now take into account conds. (#8307) comfyanonymous 2025-05-27 12:09:05 -07:00
• c9e1821a7b ComfyUI version 0.3.37 comfyanonymous 2025-05-27 07:07:44 -04:00
• f58f0f5696 More API nodes: Gemini/Open AI Chat, Tripo, Rodin, Runway Image (#8295) Robin Huang 2025-05-27 00:00:58 -07:00
• 3a10b9641c [BugFix] Update frontend to 1.20.6 (#8296) filtered 2025-05-27 16:47:06 +10:00
• 89a84e32d2 Disable initial GPU load when novram is used. (#8294) comfyanonymous 2025-05-26 13:39:27 -07:00
• e5799c4899 Enable pytorch attention by default on AMD gfx1151 (#8282) comfyanonymous 2025-05-26 01:29:25 -07:00
• a0651359d7 Return proper error if diffusion model not detected properly. (#8272) comfyanonymous 2025-05-25 02:28:11 -07:00
• ad3bd8aa49 ComfyUI version 0.3.36 comfyanonymous 2025-05-24 17:30:37 -04:00
• 5a87757ef9 Better error if sageattention is installed but a dependency is missing. (#8264) comfyanonymous 2025-05-24 03:43:12 -07:00
• 464aece92b update frontend package to v1.20.5 (#8260) Christian Byrne 2025-05-23 21:53:49 -07:00
• 0b50d4c0db Add argument to explicitly enable fp8 compute support. (#8257) comfyanonymous 2025-05-23 14:43:50 -07:00
• 30b2eb8a93 create arange on-device (#8255) drhead 2025-05-23 16:15:06 -04:00
• f85c08df06 Make VACE conditionings stackable. (#8240) comfyanonymous 2025-05-22 16:22:26 -07:00
• 4202e956a0 Add append feature to conditioning_set_values (#8239) comfyanonymous 2025-05-22 05:11:13 -07:00
• b838c36720 remove mtl from 3d model file list (#8192) Terry Jia 2025-05-22 08:08:36 -04:00
• fc39184ea9 Update frontend to 1.20 (#8232) Chenlei Hu 2025-05-22 02:24:36 -04:00
• ded60c33a0 Update templates to 0.1.18 (#8224) ComfyUI Wiki 2025-05-22 02:40:08 +08:00
• 8bb858e4d3 Improve performance with large number of queued prompts (#8176) Michael Abrahams 2025-05-21 05:14:17 -04:00
• 57893c843f Code Optimization and Issues Fixes in ComfyUI server (#8196) 编程界的小学生 2025-05-21 16:59:42 +08:00
• 65da29aaa9 Make torch.compile LoRA/key-compatible (#8213) Jedrzej Kosinski 2025-05-21 01:56:56 -07:00
• 10024a38ea ComfyUI version v0.3.35 comfyanonymous 2025-05-21 04:50:37 -04:00
• 87f9130778 Revert "This doesn't seem to be needed on chroma. (#8209)" (#8210) comfyanonymous 2025-05-20 02:39:55 -07:00