Alexander Piskun
f9acbccf0a
Enable External Event Loop Integration for ComfyUI [refactor] ( #6114 )
...
* Refactor main.py to support external event loop integration
* added optional "asyncio_loop" argument to allow using existing event loop
---------
Signed-off-by: bigcat88 <bigcat88@icloud.com>
2024-12-24 06:38:52 -05:00
comfyanonymous
9946fff072
Add temporal tiling to VAE Decode (Tiled) node.
...
You can now do tiled VAE decoding on the temporal direction for videos.
2024-12-23 20:03:37 -05:00
Chenlei Hu
21e330a8d8
Use raw dir name to serve static web content ( #6107 )
2024-12-23 03:29:42 -05:00
comfyanonymous
6b963ebdc5
Add a try except block so if torch version is weird it won't crash.
2024-12-23 03:22:48 -05:00
Simon Lui
668cc89307
Add oneAPI device selector for xpu and some other changes. ( #6112 )
...
* Add oneAPI device selector and some other minor changes.
* Fix device selector variable name.
* Flip minor version check sign.
* Undo changes to README.md.
2024-12-23 03:18:32 -05:00
comfyanonymous
e7747a1e35
Make --novram completely offload weights.
...
This flag is mainly used for testing the weight offloading, it shouldn't
actually be used in practice.
Remove useless import.
2024-12-23 01:51:08 -05:00
comfyanonymous
f1edcbd074
Comment out some useless code.
2024-12-22 23:51:14 -05:00
zhangp365
69518a310f
fixed a bug in ldm/pixart/blocks.py ( #6158 )
2024-12-22 23:44:20 -05:00
comfyanonymous
e440136a18
Fix lowvram issue with ltxv vae.
2024-12-22 23:20:17 -05:00
comfyanonymous
12f0beabf0
Relax minimum ratio of weights loaded in memory on nvidia.
...
This should make it possible to do higher res images/longer videos by
further offloading weights to CPU memory.
Please report an issue if this slows down things on your system.
2024-12-22 03:06:37 -05:00
comfyanonymous
e023ab9d80
Add that Hunyuan Video and Pixart are supported to readme.
...
Clean up the supported models part of the readme.
2024-12-21 11:31:39 -05:00
TechnoByte
85b05078aa
remove minimum step count for AYS ( #6137 )
...
The 10 step minimum for the AYS scheduler is pointless, it works well at lower steps, like 8 steps, or even 4 steps.
For example with LCM or DMD2.
Example here: https://i.ibb.co/56CSPMj/image.png
2024-12-21 10:05:09 -05:00
Qiacheng Li
160c4e2335
Update README.md for Intel GPUs ( #6069 )
2024-12-20 18:04:03 -05:00
comfyanonymous
b38caef86c
Get rid of meshgrid warning.
2024-12-20 18:02:12 -05:00
comfyanonymous
03e2a443b2
Remove useless code.
2024-12-20 17:50:03 -05:00
comfyanonymous
058c9d8df0
Remove some useless code.
2024-12-20 17:43:50 -05:00
comfyanonymous
1dc3f45101
Some fixes/cleanups to pixart code.
...
Commented out the masking related code because it is never used in this
implementation.
2024-12-20 17:10:52 -05:00
Chenlei Hu
917717a0a4
Replace print with logging ( #6138 )
...
* Replace print with logging
* nit
* nit
* nit
* nit
* nit
* nit
2024-12-20 16:24:55 -05:00
City
a3a893abeb
Add PixArt model support ( #6055 )
...
* PixArt initial version
* PixArt Diffusers convert logic
* pos_emb and interpolation logic
* Reduce duplicate code
* Formatting
* Use optimized attention
* Edit empty token logic
* Basic PixArt LoRA support
* Fix aspect ratio logic
* PixArtAlpha text encode with conds
* Use same detection key logic for PixArt diffusers
2024-12-20 15:25:00 -05:00
comfyanonymous
de547c1399
Support new LTXV VAE.
2024-12-20 04:38:29 -05:00
comfyanonymous
f4902ea0d4
Fix some more video tiled encode issues.
...
The downscale_ratio formula for the temporal had issues with some frame
numbers.
2024-12-19 23:14:03 -05:00
comfyanonymous
2c10a7611b
Fix tiled hunyuan video VAE encode issue.
...
Some shapes like 1024x1024 with tile_size 256 and overlap 64 had issues.
2024-12-19 22:55:15 -05:00
catboxanon
bfd792e8b0
Support preview images embedded in safetensors metadata ( #6119 )
...
* Support preview images embedded in safetensors metadata
* Add unit test for safetensors embedded image previews
2024-12-19 14:01:56 -08:00
comfyanonymous
7225891b48
More proper fix for the memory issue.
2024-12-19 16:21:56 -05:00
comfyanonymous
8b07be7800
Fix lowvram bug when using a model multiple times in a row.
...
The memory system would load an extra 64MB each time until either the
model was completely in memory or OOM.
2024-12-19 16:04:56 -05:00
comfyanonymous
6eefe6a53b
Make VAE Encode tiled node work with video VAE.
2024-12-19 05:31:39 -05:00
comfyanonymous
56c023f2fb
Add fast previews for hunyuan video.
2024-12-18 18:24:23 -05:00
comfyanonymous
c558cea96a
Small optimizations.
2024-12-18 18:23:28 -05:00
Chenlei Hu
76f5591fb0
Add .github folder to maintainer owner list ( #6027 )
2024-12-18 15:06:53 -05:00
Chenlei Hu
8755839453
Update web content to release v1.5.19 ( #6105 )
2024-12-18 15:06:20 -05:00
comfyanonymous
9181dbaaa8
Support old diffusion-pipe hunyuan video loras.
2024-12-18 06:23:54 -05:00
comfyanonymous
97a136ffa2
Fix regression in VAE code on old pytorch versions.
2024-12-18 03:08:28 -05:00
comfyanonymous
a46c5f7e28
Add ConditioningStableAudio.
...
This lets you control the seconds_start and seconds_total parameters for
the Stable Audio model.
2024-12-18 03:01:12 -05:00
comfyanonymous
8dc45adbe4
Add: --use-sage-attention to enable SageAttention.
...
You need to have the library installed first.
2024-12-18 01:56:10 -05:00
comfyanonymous
fd5d3147dc
Pick attention implementation based on device in llama code.
2024-12-18 01:30:20 -05:00
comfyanonymous
5ea21ff2b2
Properly tokenize the template for hunyuan video.
2024-12-17 16:22:02 -05:00
comfyanonymous
42a53bfe5a
Fix tiled vae not working with some shapes.
2024-12-17 16:22:02 -05:00
Terry Jia
b201130839
add preview 3d node ( #6070 )
...
* add preview 3d node
* mark 3d nodes as EXPERIMENTAL
2024-12-17 10:42:24 -08:00
comfyanonymous
021ca47559
Support diffusion-pipe hunyuan video lora format.
2024-12-17 07:14:21 -05:00
comfyanonymous
aa5005ff35
Support llama hunyuan video text encoder in scaled fp8 format.
2024-12-17 04:19:22 -05:00
comfyanonymous
4645275c35
Fix regression with ltxv VAE.
2024-12-17 02:17:31 -05:00
comfyanonymous
f642cc115b
Adjust used dtypes for hunyuan video VAE and diffusion model.
2024-12-16 23:31:10 -05:00
comfyanonymous
7fa7a5b733
Add some missing imports.
2024-12-16 19:42:01 -05:00
comfyanonymous
2b49852ca2
Basic Hunyuan Video model support.
2024-12-16 19:35:40 -05:00
comfyanonymous
f426e83a83
Don't expand mask when not necessary.
...
Expanding seems to slow down inference.
2024-12-16 18:22:50 -05:00
Raphael Walker
ec2ea78501
Add support for attention masking in Flux ( #5942 )
...
* fix attention OOM in xformers
* allow passing attention mask in flux attention
* allow an attn_mask in flux
* attn masks can be done using replace patches instead of a separate dict
* fix return types
* fix return order
* enumerate
* patch the right keys
* arg names
* fix a silly bug
* fix xformers masks
* replace match with if, elif, else
* mask with image_ref_size
* remove unused import
* remove unused import 2
* fix pytorch/xformers attention
This corrects a weird inconsistency with skip_reshape.
It also allows masks of various shapes to be passed, which will be
automtically expanded (in a memory-efficient way) to a size that is
compatible with xformers or pytorch sdpa respectively.
* fix mask shapes
2024-12-16 18:21:17 -05:00
Alexander Dyadyun
87d9bdacb1
Update README.md ( #6071 )
...
The last ROCM 6.2 build was November 22nd, after that date new builds use ROCM 6.2.4.
The builds from the new URL have been tested and work without problems.
2024-12-16 15:24:54 -05:00
Chenlei Hu
7a27c3c794
Update web content to release v1.5.18 ( #6075 )
2024-12-16 11:38:24 -08:00
Terry Jia
5a9ad12c8c
use String directly to set bg color for load 3d canvas ( #6057 )
2024-12-16 10:51:40 -08:00
comfyanonymous
07c0e793b9
Fix case of ExecutionBlocker not handled correctly with INPUT_IS_LIST.
2024-12-15 08:41:35 -05:00
