comfyanonymous
1176023ebb
Improved memory management. ( #5450 )
...
* Less fragile memory management.
* Fix issue.
* Remove useless function.
* Prevent and detect some types of memory leaks.
* Run garbage collector when switching workflow if needed.
* Fix issue.
2024-12-02 14:39:34 -05:00
comfyanonymous
c690e318b1
Remove useless code.
2024-12-02 06:49:55 -05:00
comfyanonymous
797c883f33
make dpm_2_ancestral work with rectified flow.
2024-12-01 07:37:41 -05:00
comfyanonymous
1977e68f8e
Add basic style model "multiply" strength.
2024-11-30 07:27:11 -05:00
comfyanonymous
005e5bb549
How to enable experimental memory efficient attention on ROCm RDNA3.
2024-11-29 06:19:49 -05:00
Dr.Lt.Data
efc6b4c4b3
Backward compatibility patch for changes in the method signature of InpaintModelConditioning. ( #5825 )
...
https://github.com/comfyanonymous/ComfyUI/issues/5813
2024-11-28 20:30:28 -05:00
comfyanonymous
0b45067a00
Add a way to disable cropping in the CLIPVisionEncode node.
2024-11-28 20:24:47 -05:00
comfyanonymous
1f7974e026
Fast previews for ltxv.
2024-11-28 06:46:15 -05:00
Chenlei Hu
03f7f19602
Update web content to release v1.4.13 ( #5807 )
2024-11-28 04:59:06 -05:00
Chenlei Hu
2f7ea6598d
Remove internal model download endpoint ( #5432 )
2024-11-28 04:57:06 -05:00
comfyanonymous
767a0dfc74
Remove print.
2024-11-27 20:28:39 -05:00
comfyanonymous
e5e0a81cac
Missing parentheses.
2024-11-27 13:45:32 -05:00
comfyanonymous
37cdbf4b29
LTXV model merging node.
2024-11-27 01:43:31 -05:00
comfyanonymous
4f6b53477e
Alternative fix for #5767
2024-11-26 17:53:04 -05:00
lky
0f82b0da6b
fix multi add makedirs error ( #5786 )
...
try to start multiple comfyui server at the same time, and this got error
2024-11-26 15:34:19 -05:00
comfyanonymous
e4eba01dba
Support official SD3.5 Controlnets.
2024-11-26 11:31:25 -05:00
comfyanonymous
264d589a17
Support for the official mochi lora format.
2024-11-26 03:34:36 -05:00
comfyanonymous
fd97a4f060
Flux inpaint model does not work in fp16.
2024-11-26 01:33:01 -05:00
comfyanonymous
df553487ed
Add option to inference the diffusion model in fp32 and fp64.
2024-11-25 05:00:23 -05:00
comfyanonymous
d58e4221a0
Skip layer guidance now works on hydit model.
2024-11-24 05:54:30 -05:00
40476
598a8417d2
Update README.md ( #5707 )
2024-11-24 04:12:07 -05:00
spacepxl
18235fdc4d
set LTX min length to 1 for t2i ( #5750 )
...
At length=1, the LTX model can do txt2img and img2img with no other changes required.
2024-11-23 21:33:08 -05:00
comfyanonymous
7b6d4188ce
Skip layer guidance node now works on LTX-Video.
2024-11-23 10:33:05 -05:00
comfyanonymous
65bd54db28
Some improvements to the lowvram unloading.
2024-11-22 20:59:15 -05:00
comfyanonymous
26693883d1
Fix some tiled VAE decoding issues with LTX-Video.
2024-11-22 18:00:34 -05:00
comfyanonymous
6c237ebcd8
LTXV lowvram fixes.
2024-11-22 17:17:11 -05:00
comfyanonymous
a23a1ca42a
Some fixes to the lowvram system.
2024-11-22 16:40:04 -05:00
comfyanonymous
2f708b29c9
Remove prints.
2024-11-22 10:51:31 -05:00
comfyanonymous
4004280bba
Remove print.
2024-11-22 10:49:15 -05:00
comfyanonymous
c307d646f7
Add LTX-Video support to the Readme.
2024-11-22 09:24:20 -05:00
comfyanonymous
8f3fabbfe5
Support Lightricks LTX-Video model.
2024-11-22 08:46:39 -05:00
comfyanonymous
0c21ed154e
Fix mask issue in some attention functions.
2024-11-22 02:10:09 -05:00
comfyanonymous
c348659633
Support new flux model variants.
2024-11-21 08:38:23 -05:00
comfyanonymous
cbd4c21086
Add some new weight patching functionality.
...
Add a way to reshape lora weights.
Allow weight patches to all weight not just .weight and .bias
Add a way for a lora to set a weight to a specific value.
2024-11-21 07:19:17 -05:00
comfyanonymous
dc18b258e4
Update readme.
2024-11-20 20:42:51 -05:00
comfyanonymous
bb7614876f
Fix mask issue with attention_xformers.
2024-11-20 17:07:46 -05:00
comfyanonymous
23c4ff672f
Skip layer guidance now works on stable audio model.
2024-11-20 07:33:06 -05:00
comfyanonymous
fbcc78ce1a
Rename add_noise_mask -> noise_mask.
2024-11-19 15:31:09 -05:00
comfyanonymous
b87e22d624
Add boolean to InpaintModelConditioning to disable the noise mask.
2024-11-19 07:31:29 -05:00
Yoland Yan
ac4164e3a8
Add terminal size fallback ( #5623 )
2024-11-19 03:34:20 -05:00
comfyanonymous
add024b9ac
Refactor inpaint/ip2p code.
2024-11-19 03:25:25 -05:00
Chenlei Hu
1d50980167
Update UI screenshot in README ( #5666 )
...
* Update UI ScreenShot in README
* Remove legacy UI screenshot file
* nit
* nit
2024-11-18 16:50:34 -05:00
comfyanonymous
bcd7048d69
Add a skip layer guidance node that can also skip single layers.
...
This one should work for skipping the single layers of models like Flux
and Auraflow.
If you want to see how these models work and how many double/single layers
they have see the "ModelMerge*" nodes for the specific model.
2024-11-18 02:20:43 -05:00
comfyanonymous
e7d2871d48
Support block replace patches in auraflow.
2024-11-17 08:19:59 -05:00
comfyanonymous
46f295c579
Add transformer options blocks replace patch to mochi.
2024-11-16 20:48:14 -05:00
Chenlei Hu
d8e1f1aa63
Fix 3.8 compatibility in user_manager.py ( #5645 )
2024-11-16 20:42:21 -05:00
Chenlei Hu
884d70e752
Update web content to release v1.3.44 ( #5620 )
...
* Update web content to release v1.3.44
* nit
2024-11-15 20:17:15 -05:00
comfyanonymous
eaf6cca12e
Add a node to block merge auraflow models.
2024-11-15 12:47:55 -05:00
comfyanonymous
ee5fe74e24
Add advanced model merging node for mochi.
2024-11-14 07:51:20 -05:00
comfyanonymous
84e6dd9c8a
Fix issue with 3d masks.
2024-11-13 07:18:30 -05:00
