Chenlei Hu
6d8a441e69
Fix routes ( #3790 )
2024-06-19 22:36:31 -04:00
comfyanonymous
aeac10ce20
Fix issue with full diffusers SD3 loras.
2024-06-19 22:32:04 -04:00
comfyanonymous
eabd70d64d
Support loading diffusers SD3 model format with UNETLoader node.
2024-06-19 22:21:18 -04:00
comfyanonymous
5d8206517c
Remove empty line.
2024-06-19 20:20:35 -04:00
Mario Klingemann
c39be91219
Update sd1_clip.py ( #3684 )
...
Made token instance check more flexible so it also works with integers from numpy arrays or long tensors
2024-06-19 16:42:41 -04:00
comfyanonymous
9c26d62191
Add ipndm sampler.
2024-06-19 16:32:30 -04:00
Chenlei Hu
9c45930fd4
Add api/ prefix to api endpoints ( #3779 )
2024-06-19 10:39:17 -04:00
comfyanonymous
ffc4037b46
Support full SD3 loras.
2024-06-19 10:13:33 -04:00
comfyanonymous
77a0e5a4fb
Add soundfile dependency so that windows can save audio.
2024-06-18 09:57:40 -04:00
comfyanonymous
f3754bf8f3
Basic tiled decoding for audio VAE.
2024-06-17 22:48:23 -04:00
Juanjuan
86a79ec55a
fix app.js no graph defined ( #3754 )
...
* local test
* fix "graph" not found
* fix
---------
Co-authored-by: Xiujuan Li <xiujuali@amazon.com>
2024-06-17 07:56:53 -04:00
Janek Mann
95028b4402
Fix lora keys for SimpleTuner ( #3759 )
2024-06-17 07:55:06 -04:00
comfyanonymous
160c550977
Use fp16 as the default vae dtype for the audio VAE.
2024-06-16 13:12:54 -04:00
comfyanonymous
928c1989f6
Squash depreciation warning on new pytorch.
2024-06-16 13:06:23 -04:00
comfyanonymous
cf352f2936
Better estimation for memory usage during audio VAE encoding/decoding.
2024-06-16 11:47:32 -04:00
comfyanonymous
04de2cea4e
Fix VAEEncode with taesd3.
2024-06-16 03:10:04 -04:00
comfyanonymous
59781392b3
Improvements to the TAESD3 implementation.
2024-06-16 02:04:24 -04:00
Dr.Lt.Data
ce165da821
support TAESD3 ( #3738 )
2024-06-16 02:03:53 -04:00
comfyanonymous
1eb91dbfbb
Initial support for the stable audio open model.
2024-06-15 12:14:56 -04:00
comfyanonymous
97af65d0dc
Small optimization.
2024-06-15 02:44:38 -04:00
comfyanonymous
5c5911a0c1
Optimize some unneeded if conditions in the sampling code.
2024-06-15 02:26:19 -04:00
comfyanonymous
12e44a5d50
Add a --force-channels-last to inference models in channel last mode.
2024-06-15 01:08:12 -04:00
comfyanonymous
8dbd876a23
Print key names for easier debugging.
2024-06-14 18:18:53 -04:00
Simon Lui
20052d83b5
Exempt IPEX from non_blocking previews fixing segmentation faults. ( #3708 )
2024-06-13 18:51:14 -04:00
comfyanonymous
77b1aa430f
Support SD3 diffusers lora.
2024-06-13 18:26:10 -04:00
comfyanonymous
468f9b8d49
Support setting weight offsets in weight patcher.
2024-06-13 17:21:26 -04:00
comfyanonymous
b9aea52255
Fix lowvram issue.
2024-06-12 10:39:33 -04:00
comfyanonymous
edde4b7d4d
Fix regular empty latent image not working with SD3 and custom sampler.
2024-06-12 10:32:34 -04:00
comfyanonymous
c865d9d71b
Add link to SD3 example page to README.
2024-06-12 09:48:27 -04:00
comfyanonymous
7d328e3b3e
Default shift value on SD3 is 3.0
2024-06-12 02:24:39 -04:00
comfyanonymous
4514807781
Don't auto convert clip and vae weights to fp16 when saving checkpoint.
2024-06-12 01:07:58 -04:00
comfyanonymous
5159a8fd8c
Save SD3 modelspec.architecture in CheckpointSave node.
2024-06-12 01:02:07 -04:00
comfyanonymous
4a6dfb619d
SD3 better memory usage estimation.
2024-06-12 00:49:00 -04:00
comfyanonymous
9d4f62e30d
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
917810a2c6
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
2024-06-11 17:03:26 -04:00
comfyanonymous
c7e715e64a
Support multiple text encoder configurations on SD3.
2024-06-11 13:14:43 -04:00
comfyanonymous
6aa3b74a95
Update EmptySD3LatentImage to use 1024 resolution by default.
2024-06-11 07:37:22 -04:00
comfyanonymous
0f719c05f1
Reuse code.
2024-06-11 07:20:26 -04:00
Dango233
8c3b1af91f
Remove redundancy in mmdit.py ( #3685 )
2024-06-11 06:30:25 -04:00
comfyanonymous
75e5795758
Require safetensors library to be at least 0.4.2 for fp8 support.
2024-06-11 06:26:13 -04:00
comfyanonymous
71ed9026b0
Fix bug with cosxl edit model.
2024-06-10 16:00:03 -04:00
comfyanonymous
cc2f32af2c
SD3 Support.
2024-06-10 14:06:23 -04:00
comfyanonymous
258e685fcc
Support sampling non 2D latents.
2024-06-10 01:31:09 -04:00
comfyanonymous
a2a20c27f4
Support zeroing out text embeddings with the attention mask.
2024-06-09 16:51:58 -04:00
comfyanonymous
372b1130d1
Reshape the empty latent image to the right amount of channels if needed.
2024-06-08 02:35:08 -04:00
comfyanonymous
add86d4eb5
Use the end token for the text encoder attention mask.
2024-06-07 03:05:23 -04:00
comfyanonymous
ef2a2a670e
Remove some unnecessary arguments.
2024-06-06 14:49:45 -04:00
comfyanonymous
b6a9851535
Add function to get the list of currently loaded models.
2024-06-05 23:25:16 -04:00
comfyanonymous
20f463902f
pytorch xpu should be flash or mem efficient attention?
2024-06-04 17:44:14 -04:00
Denys Smirnov
675326c9ab
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 83773598.
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
