kijai
4a3ab6958a
Update nodes.py
2025-12-12 15:43:48 +02:00
kijai
91413b33f5
One-to-all pose cfg
2025-12-12 15:23:56 +02:00
kijai
60b3ec57dd
Support 1.3B OneToAll
2025-12-12 12:32:04 +02:00
kijai
f6e2d6dd47
version 1.4.2
2025-12-11 17:43:31 +02:00
kijai
68d65979d6
Fix crash on latest frontend version
2025-12-11 17:30:08 +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
7273470faa
Optimize trajectory drawing
2025-12-10 20:08:54 +02:00
kijai
c36e56875e
Update nodes.py
2025-12-10 20:05:49 +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
369043c5d8
Add comfy core attention as option
...
For edge cases that may benefit from the older attention types
2025-12-10 19:39:05 +02:00
Jukka Seppänen
eb6dd96049
Merge pull request #1749 from wong00/fix-flashattn3-attention-compute
...
[bugfix] Fixed the logic of computing attention in flashAttention3.
2025-12-10 11:52:18 +02:00
wangxin68
38a48c670a
[bugfix] Fixed the logic for processing return values after computing attention in flashAttention3
2025-12-10 17:27:37 +08:00
kijai
dd58511d4e
Expose some WanMove track preview drawing options
...
Don't need to be so huge
2025-12-10 02:26:51 +02:00
kijai
4c97d27583
Fix LongCat error
2025-12-09 21:09:44 +02:00
kijai
bcdc0c0661
Add node to use WanMove with native workflows
2025-12-09 21:04:56 +02:00
kijai
83c25644ef
Create wanvideo_WanMove_I2V_example_01.json
2025-12-09 20:28:45 +02:00
kijai
113b6df04d
Fix multiple tracks
2025-12-09 20:11:45 +02:00
kijai
d000fbc645
Support WanMove
...
https://github.com/ali-vilab/Wan-Move
2025-12-09 19:55:56 +02:00
kijai
cc58964027
Refactor init.py to something more sensible
2025-12-09 19:53:26 +02:00
kijai
fa57681424
Reduce recompiles with unmerged loras
2025-12-09 14:40:52 +02:00
kijai
0a65354247
Allow larger wananimate window size for disabling windowing
2025-12-09 14:15:00 +02:00
kijai
a27a4892b6
version 1.4.1
2025-12-09 12:56:40 +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
e867e642d4
Fix longcat scheduler
2025-12-08 10:26:38 +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
7f9560eb33
Fix mistake in sageattn_ultravico
2025-12-07 19:56:03 +02:00
kijai
2369cdbbe9
Fix prompt splitting
2025-12-07 18:34:21 +02:00
kijai
123c9ca312
Allow HuMo to work with start_image
2025-12-07 18:18:16 +02:00
kijai
2b62866945
Fix SteadyDancer GGUF dtypes
2025-12-06 17:25:57 +02:00
kijai
b5415573c5
Update nodes_model_loading.py
2025-12-05 20:55:33 +02:00
kijai
9e005fab90
Fix scaling for light TAE
2025-12-05 14:03:33 +02:00
kijai
f85ea5a48a
add "empty_frame_pad_image" input to I2V encode node for easier SVI lora use
...
This pads the empty frames with the given image, as should be done with SVI-shot and SVI 2.0 LoRAs
2025-12-05 13:05:35 +02:00
kijai
ee1bb5c5c7
Update nodes_utility.py
2025-12-05 12:07:48 +02:00
kijai
041c31fe2e
cleanup
2025-12-05 12:01:34 +02:00
kijai
4e7b8dd92c
Clearer error on attention mode imports
2025-12-05 02:00:31 +02:00
kijai
e2333d0f04
Update nodes_sampler.py
2025-12-04 16:51:30 +02:00
kijai
2dd4c6bf15
Merge branch 'pr/1705'
2025-12-04 16:48:50 +02:00
kijai
9d0a21228b
Update nodes_sampler.py
2025-12-04 16:48:23 +02:00
kijai
001bc0e24a
Merge branch 'main' of https://github.com/kijai/ComfyUI-WanVideoWrapper
2025-12-04 16:44:29 +02:00
kijai
7189922f36
Update __init__.py
2025-12-04 16:44:18 +02:00
kijai
faf9c5927d
Merge branch 'pr/1510'
2025-12-04 16:44:02 +02:00
Jukka Seppänen
6c5dc0ba2a
Merge pull request #1546 from wzxysf/main
...
Enable vae tiling with end frame
2025-12-04 16:40:29 +02:00
Jukka Seppänen
995804166d
Merge pull request #1651 from jamesjjcondon/patch-1
...
Refactor data_mean and data_std initialization
2025-12-04 16:40:05 +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
b06c7d2d6d
Add UltraViCo -sage attention mode and refactor some attention code
...
https://github.com/thu-ml/DiT-Extrapolation/
2025-12-03 13:32:45 +02:00
kijai
014e711972
cleanup
2025-12-03 11:09:09 +02:00
kijai
c47b1ded69
Apply conv3d workaround to UniAnimate
2025-12-02 15:00:06 +02:00
kijai
7bc45daaf2
Cleanup whitespaces
2025-12-02 14:50:26 +02:00