kijai
3aae54f220
Allow WanMove to work with context windows
2025-12-15 01:22:21 +02:00
kijai
3611341339
Fix uni3c reloading
2025-12-14 16:48:55 +02:00
kijai
0fa5383106
Fix default rope for v2 sampler
2025-12-13 16:09:08 +02:00
kijai
78e3e1857c
Add v2 sampling nodes for cleaner workflows
...
No functional changes, just cleaner nodes
2025-12-13 15:42:35 +02:00
kijai
91413b33f5
One-to-all pose cfg
2025-12-12 15:23:56 +02:00
kijai
66a21e544a
WanMove: Make compatible with TRACK -input type and make strength param do something
2025-12-11 01:45:05 +02:00
kijai
f9287e3ecd
Fix cfg when using WanMove
2025-12-10 20:05:41 +02:00
kijai
2790c532cc
Handle OneToAll extra layer devices
2025-12-10 19:46:02 +02:00
kijai
d000fbc645
Support WanMove
...
https://github.com/ali-vilab/Wan-Move
2025-12-09 19:55:56 +02:00
kijai
8b037bce2e
Squashed commit of the following:
...
commit c3eb0f49faf68ab953f1b08b7e00225e041e5d0b
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Tue Dec 9 12:55:49 2025 +0200
move workflow
commit e129e25c26f9b55b527dd3e9f15c6e3f215af11f
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Tue Dec 9 11:17:17 2025 +0200
Fix padding
commit f252f34eff5cc15ec6fc475f929cafa3e5b7f46c
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Tue Dec 9 01:38:17 2025 +0200
Add long video example
commit 09ceab808b67a3b2fb7d1ee5fc0a1ad667739e2a
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Tue Dec 9 01:31:48 2025 +0200
Support extension
commit 7ca221874e8a2cabfc766c51bb63774fde3c851b
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 12:28:29 2025 +0200
Might as well not even do control pass on uncond...
commit b55caf299e4d89148f5885e8e56bf8e411472dc3
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 12:15:59 2025 +0200
Cfg fixes
commit fd54ba23e6746acb33a8bf124e5bc7de9d947ff1
Merge: 2f97b1b e867e64
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 10:39:55 2025 +0200
Merge branch 'main' into onetoall
commit 2f97b1bd887367962542b9a6058f9f6e3c4ad4d7
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 09:32:09 2025 +0200
Add ref_mask input
commit 74cad232fd35347c50f2ed7465ff13e179ef8402
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 03:44:42 2025 +0200
Update nodes_model_loading.py
commit 01a038eb4a30f29d868fbaef190e6e90da1a058d
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 03:11:08 2025 +0200
Fix indentation
commit a95f4d6eaa4468e818910fec7ba11e1f92423d9b
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 02:54:47 2025 +0200
Update model.py
commit ad006985a1bafdf5941c0fa85a47852eb20a818a
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 02:54:19 2025 +0200
Fix token replace
commit b5f0f44f1720586950756ad142a538e04814270f
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 02:50:52 2025 +0200
Don't use token replace by default
commit 874174ec2921c528a4373097fd0bebbbb5257606
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 02:24:47 2025 +0200
Create WanToAllAnimation_test.json
commit 9e6175855618c94c1bcb89c4b89879219410ce53
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 02:23:15 2025 +0200
Add token replacement
commit 41fd76dfcbf0e70a3a7308a6fa0652fb492ed1f6
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 00:45:33 2025 +0200
Use correct norm for reference attn
commit 705f5dcc8b6cd5fa6fe453f9bd01ffdf43a23078
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Dec 8 00:11:17 2025 +0200
cleanup
commit 4f095d97f80da807417d49d9aa7e9ee47145c85f
Merge: 3e4e4db 2369cdb
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Dec 7 18:44:01 2025 +0200
Merge branch 'main' into onetoall
commit 3e4e4db35d3e266c39d48cd683f60384a737eca5
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Dec 7 00:27:23 2025 +0200
handle controlnet better
commit c5742552a9af4a3ae208f9c2ead6e1105cc2c348
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Dec 6 17:24:45 2025 +0200
cleanup
commit c06ff9c06651c32953236802bd7fb385b9cf93ab
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Dec 6 03:41:02 2025 +0200
3D rope for controlnet
commit 948ea6b783f54892515cbc9cfe66484913904ee7
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Dec 6 03:08:04 2025 +0200
pose input scaling
commit 90c2eff3b2d30d3a92ff5c27e4327a0ac80b642c
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Dec 6 02:37:48 2025 +0200
Cleanup
commit 9f7683422c1aa8ebe4d3380a86be98d6c589b270
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Dec 5 23:29:05 2025 +0200
pose control
commit 0f217be4d8742741b0f89db50138214302a58dc3
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Dec 5 20:55:10 2025 +0200
Support reference input
2025-12-09 12:56:11 +02:00
kijai
00971fc121
Don't remove lora in loop sampling offload
2025-12-08 09:43:36 +02:00
Jukka Seppänen
0e81adb843
Fix for HuMo with I2V
2025-12-08 03:17:29 +02:00
kijai
123c9ca312
Allow HuMo to work with start_image
2025-12-07 18:18:16 +02:00
kijai
e2333d0f04
Update nodes_sampler.py
2025-12-04 16:51:30 +02:00
kijai
9d0a21228b
Update nodes_sampler.py
2025-12-04 16:48:23 +02:00
mossmatrix
4e2bf0f1fa
Fix device mismatch error with I2V + Lynx embeds
...
Fixed RuntimeError when using I2V embeds with Lynx embeds where tensors
were on different devices (cuda:0 and cpu).
The issue occurred because lynx_ref_text_embed["prompt_embeds"] were not
explicitly moved to the GPU device before being passed to the transformer
during Lynx reference buffer extraction.
Changes:
- Move lynx text embeddings to device in both conditional and unconditional
buffer extraction calls (lines 1114 and 1128)
- Ensures all tensors are on the same device during cross-attention operations
2025-12-04 00:34:54 -05:00
kijai
aebeeb9160
Code cleanup
2025-12-02 14:49:42 +02:00
kijai
a652c55bf7
Remove LoRAs when fully offloading as well
2025-12-01 12:50:22 +02:00
kijai
0c9d5b8dcc
context windows
2025-11-29 02:11:57 +02:00
kijai
e54fa5d059
Init
2025-11-28 20:32:16 +02:00
kijai
f872460285
Fix TTM for dual sampler setups
2025-11-16 19:23:19 +02:00
kijai
b826642a83
Add TTM support (Time To Move)
...
https://github.com/time-to-move/TTM
2025-11-16 17:52:49 +02:00
kijai
e3c2a1431b
Squashed commit of the following:
...
commit f685ee33ac
Merge: bb5707f 4e31081
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 13 16:37:38 2025 +0200
Merge branch 'main' into bindweave
commit bb5707f601
Merge: acb662b ff26836
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Tue Nov 11 18:53:19 2025 +0200
Merge branch 'main' into bindweave
commit acb662b5af
Merge: 907c9e1 e926f7a
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Tue Nov 11 11:44:26 2025 +0200
Merge branch 'main' into bindweave
commit 907c9e1cdd
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Mon Nov 10 21:02:58 2025 +0200
Update nodes.py
commit e4a4d22537
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Nov 8 16:04:55 2025 +0200
Update nodes_sampler.py
commit a3b2f67337
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Nov 8 16:03:00 2025 +0200
Pad clip vision embeds like in original code
commit 1e00c8fb28
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Nov 8 12:21:11 2025 +0200
Update nodes.py
commit ff16dce5c0
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Nov 7 01:15:13 2025 +0200
Update nodes_sampler.py
commit f972b31bf2
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Nov 7 01:09:22 2025 +0200
Update nodes.py
commit 3dacd6a719
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Nov 7 00:45:06 2025 +0200
Update nodes_sampler.py
commit 7bf99791ad
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Nov 7 00:44:13 2025 +0200
Update nodes.py
commit 7a5587b5af
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Fri Nov 7 00:39:10 2025 +0200
Let the user resize for QwenVL
Seems to need smaller resolutions
commit d6cf172846
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 6 23:41:24 2025 +0200
Update nodes.py
commit cf86f4f0a4
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 6 21:01:03 2025 +0200
Update model.py
commit b1f8309a20
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 6 19:55:54 2025 +0200
Update nodes_model_loading.py
commit 8992c6af64
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 6 19:22:56 2025 +0200
Don't include padding for scheduler
commit e4084a961b
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 6 18:32:53 2025 +0200
Update nodes.py
commit 3ec1edefbe
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Nov 6 17:35:48 2025 +0200
init
For testing, no idea if it works yet
2025-11-13 17:10:57 +02:00
kijai
68392684b5
Add node to use UniLumos
...
Simply allows fore and background latent inputs for UniLumos relight model, example inputs seem to work: https://github.com/alibaba-damo-academy/Lumos-Custom/tree/main/UniLumos/UniLumos/examples
2025-11-10 19:06:45 +02:00
kijai
475f96aede
Fix accidental positional arg
2025-11-04 20:53:46 +02:00
kijai
9fa4140159
Make lora torch.compile optional for unmerged lora application
...
This change has caused issues especially with LoRAs that have dynamic rank. Will now be disabled by default, to allow full graph with unmerged LoRAs the option to allow compile is available in the Torch Compile Settings -node
2025-11-04 01:34:51 +02:00
kijai
5f4020b12d
Fix a possible issue with Ovi audio model loading
2025-10-31 17:24:24 +02:00
kijai
95391f403d
Update nodes_sampler.py
2025-10-30 17:55:55 +02:00
kijai
a64f115d35
Fix to previous
2025-10-29 11:06:38 +02:00
kijai
e45f6f2fc4
Allow WanVideoScheduler -node to work with the looping samplers
...
Was broken for Multitalk/WanAnimate/S2V
2025-10-29 10:41:33 +02:00
kijai
d2614a9a49
Merge branch 'main' into longcat
2025-10-29 02:33:37 +02:00
kijai
1c2f17e8d7
Add utility node to split sampler from settings
...
For cleaner previews
2025-10-29 02:24:24 +02:00
kijai
c80a488f70
Use fp32 norms for other models too and other fixes
2025-10-28 01:52:48 +02:00
kijai
d504c96174
Separate attention for input images like in original
2025-10-26 19:14:47 +02:00
kijai
fb00932cad
Init
...
https://huggingface.co/Kijai/LongCat-Video_comfy/tree/main
2025-10-26 16:36:20 +02:00
kijai
aa610cde2b
VACE: Support per context window reference images
2025-10-22 11:24:30 +03:00
kijai
2ea824b9ab
Mocha: Fix context window slicing
2025-10-21 20:33:03 +03:00
kijai
54e938cd70
MoCha: Fix context window mask
2025-10-21 19:40:01 +03:00
kijai
7495db7669
Update nodes_sampler.py
2025-10-21 19:15:57 +03:00
kijai
4e36aee658
MoCha: experimental context windows support
2025-10-21 18:32:40 +03:00
unrealMJ
88defbfdd1
add MoCha
2025-10-21 09:40:54 +08:00
wenjian
487c400e8e
Fix Uni3C + Context Options compatibility issue (Issue #1491 )
...
Add uni3c_data parameter to predict_with_cfg() call in context windowing loop.
Without this parameter, Uni3C camera effects were not working when using
Context Options for long video generation. This makes the context windowing
behavior consistent with multitalk and wananimate sampling modes.
2025-10-21 02:31:47 +08:00
kijai
967d15321d
fix rcm scheduler check
2025-10-19 19:49:24 +03:00
kijai
9cd79d3d4a
Add experimental rCM scheduler
...
Based on the original code, works but doesn't feel better than dpm++_sde so far
2025-10-19 19:34:17 +03:00
kijai
a721fe3d0f
Better (hopefully) FlashVSR frame selection
...
First frame was completely discarded before
2025-10-19 13:49:40 +03:00
kijai
55463a6290
Fix audio_cfg_scale
2025-10-17 18:12:54 +03:00
kijai
9cae986648
Fix for HuMo/Phantom when using cfg
2025-10-16 13:01:21 +03:00
kijai
d2ce150490
Update nodes_sampler.py
2025-10-16 10:49:54 +03:00
Anastasiy Safari
904a019491
Another fix
2025-10-15 17:52:26 -07:00
Anastasiy Safari
be02ec93cc
Fix WanAnimate to use ref_latent without bg_images
2025-10-15 17:28:19 -07:00