Commit Graph
2500 Commits
Author SHA1 Message Date
doctorpangloss 73a11c0dbb Fix execution context interaction 2024-06-12 14:34:24 -07:00
doctorpangloss cac6690481 Add known SD3 model files, merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-06-12 10:56:41 -07:00
comfyanonymous 605e64f6d3 Fix lowvram issue. 2024-06-12 10:39:33 -04:00
comfyanonymous 0eaa34ec5b Fix regular empty latent image not working with SD3 and custom sampler. 2024-06-12 10:32:34 -04:00
comfyanonymous 321e509e0a Add link to SD3 example page to README. 2024-06-12 09:48:27 -04:00
comfyanonymous c8b5e08dc3 Default shift value on SD3 is 3.0 2024-06-12 02:24:39 -04:00
comfyanonymous 1ddf512fdc Don't auto convert clip and vae weights to fp16 when saving checkpoint. 2024-06-12 01:07:58 -04:00
comfyanonymous 32be358213 Save SD3 modelspec.architecture in CheckpointSave node. 2024-06-12 01:02:07 -04:00
comfyanonymous 694e0b48e0 SD3 better memory usage estimation. 2024-06-12 00:49:00 -04:00
comfyanonymous 69c8d6d8a6 Single and dual clip loader nodes support SD3.
You can use the CLIPLoader to use the t5xxl only or the DualCLIPLoader to
use CLIP-L and CLIP-G only for sd3.
2024-06-11 23:27:39 -04:00
comfyanonymous 0e49211a11 Load the SD3 T5xxl model in the same dtype stored in the checkpoint. 2024-06-11 17:03:26 -04:00
comfyanonymous 5889b7ca0a Support multiple text encoder configurations on SD3. 2024-06-11 13:14:43 -04:00
doctorpangloss b8e4fd4528 Controlnet++ checkpoints 2024-06-11 08:45:56 -07:00
comfyanonymous 1c34d338d7 Update EmptySD3LatentImage to use 1024 resolution by default. 2024-06-11 07:37:22 -04:00
comfyanonymous 9424522ead Reuse code. 2024-06-11 07:20:26 -04:00
Dango233andGitHub 73ce178021 Remove redundancy in mmdit.py (#3685) 2024-06-11 06:30:25 -04:00
comfyanonymous 4134564dc1 Require safetensors library to be at least 0.4.2 for fp8 support. 2024-06-11 06:26:13 -04:00
doctorpangloss 6789e9c71e Add Reference Only ControlNet hack, add ControlNet++ models 2024-06-10 20:36:23 -07:00
doctorpangloss e7682ced56 Better support for transformers t5 2024-06-10 20:22:17 -07:00
doctorpangloss 8a1557f750 Add IP Adapter nodes 2024-06-10 15:20:05 -07:00
doctorpangloss a5d828be77 Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-06-10 13:21:36 -07:00
comfyanonymous a82fae2375 Fix bug with cosxl edit model. 2024-06-10 16:00:03 -04:00
comfyanonymous 8c4a9befa7 SD3 Support. 2024-06-10 14:06:23 -04:00
doctorpangloss d778277a68 Merge with upstream and fix tests 2024-06-10 10:01:08 -07:00
comfyanonymous a5e6a632f9 Support sampling non 2D latents. 2024-06-10 01:31:09 -04:00
doctorpangloss 222e98c752 Update README 2024-06-09 15:44:36 -07:00
comfyanonymous 742d5720d1 Support zeroing out text embeddings with the attention mask. 2024-06-09 16:51:58 -04:00
comfyanonymous 6cd8ffc465 Reshape the empty latent image to the right amount of channels if needed. 2024-06-08 02:35:08 -04:00
doctorpangloss 7f300bcb7a Multi-modal LLM support and ongoing improvements to language features. 2024-06-07 16:23:10 -07:00
comfyanonymous 56333d4850 Use the end token for the text encoder attention mask. 2024-06-07 03:05:23 -04:00
doctorpangloss 6575409461 Additional chat templates to ease the use of many models. 2024-06-06 20:51:05 -07:00
doctorpangloss ebf2ef27c7 Improve LLM / language support 2024-06-06 14:57:52 -07:00
comfyanonymous 0dccb4617d Remove some unnecessary arguments. 2024-06-06 14:49:45 -04:00
comfyanonymous 104fcea0c8 Add function to get the list of currently loaded models. 2024-06-05 23:25:16 -04:00
comfyanonymous b1fd26fe9e pytorch xpu should be flash or mem efficient attention? 2024-06-04 17:44:14 -04:00
Denys SmirnovandGitHub 20447e9ec9 Fix alpha in PorterDuffImageComposite. (#3411)
There were two bugs in PorterDuffImageComposite.

The first one is the fact that it uses the mask input directly as alpha, missing the conversion (`1-a`). The fix is similar to c16f5744.

The second one is that all color composition formulas assume alpha premultiplied values, while the input is not premultiplied.

This change fixes both of these issue.
2024-06-04 16:37:11 -04:00
comfyanonymous cb8d0ebccc Don't load the view coordinates when loading a workflow from the history.
I think this makes things slightly less annoying for some users.
2024-06-03 19:48:27 -04:00
doctorpangloss 3f559135c6 Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-06-03 11:42:55 -07:00
doctorpangloss 779555aba3 Remove empty chainner __init__.py package files 2024-06-03 11:31:58 -07:00
comfyanonymous 809cc85a8e Remove useless code. 2024-06-02 19:23:37 -04:00
comfyanonymous b249862080 Add an annoying print to a function I want to remove. 2024-06-01 12:47:31 -04:00
Peter CrabtreeandGitHub e2c585f3be Fix to allow use of PerpNegGuider with cfg_function_post hooks (like PAG) (#3618) 2024-06-01 12:36:08 -04:00
doctorpangloss 5151d5b017 Include HyperSD checkpoints 2024-05-31 16:21:10 -07:00
doctorpangloss f347ac733a Fix testcontainers 2024-05-31 16:19:40 -07:00
comfyanonymous 04b308229e Small refactor of preview code. 2024-05-31 11:18:37 -04:00
doctorpangloss cb557c960b Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-05-31 07:42:11 -07:00
Benjamin BermanandGitHub aeb67d560f Fix #8 link is now correct 2024-05-31 07:23:01 -07:00
doctorpangloss 3125366eda Improve compatibility with comfyui-extra-models, improve API 2024-05-30 16:50:34 -07:00
comfyanonymous bf3e334d46 Disable non_blocking when --deterministic or directml. 2024-05-30 11:07:38 -04:00
doctorpangloss 8a3b49eb49 Resolves SSL errors on Windows when using fsspec 2024-05-29 17:42:15 -07:00