Commit Graph

2409 Commits

Author SHA1 Message Date
comfyanonymous ca9d300a80 Better estimation for memory usage during audio VAE encoding/decoding. 2024-06-16 11:47:32 -04:00
comfyanonymous 746a0410d4 Fix VAEEncode with taesd3. 2024-06-16 03:10:04 -04:00
comfyanonymous 04e8798c37 Improvements to the TAESD3 implementation. 2024-06-16 02:04:24 -04:00
Dr.Lt.Data df7db0e027
support TAESD3 (#3738) 2024-06-16 02:03:53 -04:00
comfyanonymous bb1969cab7 Initial support for the stable audio open model. 2024-06-15 12:14:56 -04:00
comfyanonymous 1281f933c1 Small optimization. 2024-06-15 02:44:38 -04:00
comfyanonymous f2e844e054 Optimize some unneeded if conditions in the sampling code. 2024-06-15 02:26:19 -04:00
comfyanonymous 0ec513d877 Add a --force-channels-last to inference models in channel last mode. 2024-06-15 01:08:12 -04:00
comfyanonymous 0e06b370db Print key names for easier debugging. 2024-06-14 18:18:53 -04:00
Simon Lui 5eb98f0092
Exempt IPEX from non_blocking previews fixing segmentation faults. (#3708) 2024-06-13 18:51:14 -04:00
comfyanonymous ac151ac169 Support SD3 diffusers lora. 2024-06-13 18:26:10 -04:00
comfyanonymous 37a08a41b3 Support setting weight offsets in weight patcher. 2024-06-13 17:21:26 -04:00
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
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
Dango233 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
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
comfyanonymous a5e6a632f9 Support sampling non 2D latents. 2024-06-10 01:31:09 -04:00
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
comfyanonymous 56333d4850 Use the end token for the text encoder attention mask. 2024-06-07 03:05:23 -04:00
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 Smirnov 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
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 Crabtree e2c585f3be
Fix to allow use of PerpNegGuider with cfg_function_post hooks (like PAG) (#3618) 2024-06-01 12:36:08 -04:00
comfyanonymous 04b308229e Small refactor of preview code. 2024-05-31 11:18:37 -04:00
comfyanonymous bf3e334d46 Disable non_blocking when --deterministic or directml. 2024-05-30 11:07:38 -04:00
comfyanonymous 71ec5b144e Update commands to install nightly pytorch in readme. 2024-05-29 00:20:02 -04:00
comfyanonymous 91542d4f8b Import spandrel_extra_arches if present.
I will not add this dependency to the default ones because models in the
spandrel_extra_arches package are non commercial and therefore not
compatible with free software licenses like the one ComfyUI uses.

If you don't mind this you can install it manually yourself.
2024-05-28 01:42:11 -04:00
JettHu b26da2245f
Fix UnetParams annotation typo (#3589) 2024-05-27 19:30:35 -04:00
comfyanonymous 0920e0e5fe Remove some unused imports. 2024-05-27 19:08:27 -04:00
luke zhang 34030fed92
improve dom widget performance (#3584) 2024-05-27 14:26:07 -04:00
Regis Gaughan, III f6a203951f
Extend core snapToGrid to LiteGraph Groups. (#3393)
Extends the core Comfy.SnapToGrid behavior for nodes to apply to LiteGraph's LGraphGroup with the same behavior. Also, pulls out redundant rounding code into util function.
2024-05-27 14:05:51 -04:00
comfyanonymous 16a493a190 Keep compatibility with some custom nodes. 2024-05-26 15:37:41 -04:00
comfyanonymous 9a151b7def Fix issue and unpin spandrel package. 2024-05-26 13:44:47 -04:00