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
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
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
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
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
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
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
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
comfyanonymous
8ef0fbfca3
Support conv3d in PatchEmbed.
2024-12-14 05:46:04 -05:00
comfyanonymous
06d5085650
Make pad_to_patch_size function work on multi dim.
2024-12-13 07:22:05 -05:00
Chenlei Hu
a1dd5bc59c
Enforce all pyflake lint rules ( #6033 )
...
* Enforce F821 undefined-name
* Enforce all pyflake lint rules
2024-12-12 19:29:37 -05:00
Chenlei Hu
abd7d241b4
Lint and fix undefined names (1/N) ( #6028 )
2024-12-12 18:55:26 -05:00
Chenlei Hu
0a418c6f50
Lint and fix undefined names (3/N) ( #6030 )
2024-12-12 18:49:40 -05:00
Chenlei Hu
efca88cfb3
Lint all unused variables ( #5989 )
...
* Enable F841
* Autofix
* Remove all unused variable assignment
2024-12-12 17:59:16 -05:00
comfyanonymous
159848ad06
Set initial load devices for te and model to mps device on mac.
2024-12-12 06:00:31 -05:00
comfyanonymous
e6abbe45c0
Support loading some checkpoint files with nested dicts.
2024-12-11 08:04:54 -05:00
comfyanonymous
baafbc0b32
Fix a few things in text enc code for models with no eos token.
2024-12-10 23:07:26 -05:00
comfyanonymous
4afc0f000a
Support different types of tokenizers.
...
Support tokenizers without an eos token.
Pass full sentences to tokenizer for more efficient tokenizing.
2024-12-10 15:03:39 -05:00
catboxanon
d70721f431
Add cond_scale to sampler_post_cfg_function ( #5985 )
2024-12-09 20:13:18 -05:00
Chenlei Hu
9bffd67fc9
Lint unused import ( #5973 )
...
* Lint unused import
* nit
* Remove unused imports
* revert fix_torch import
* nit
2024-12-09 15:24:39 -05:00
comfyanonymous
5396a5266b
Make CLIP set last layer node work with t5 models.
2024-12-09 03:57:14 -05:00
Haoming
bb62946a9e
clamp input ( #5928 )
2024-12-07 14:00:31 -05:00
comfyanonymous
e963629dae
A few improvements to #5937 .
2024-12-06 05:49:15 -05:00
