nodes/kijai-ComfyUI-WanVideoWrapper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,192 Commits 8 Branches 0 Tags
f653544f7b3bf2a6c387bb408cc241d6eef9aa74
Commit Graph
146 Commits
Author SHA1 Message Date
kijai 5c1f64197e Check for actual scale_weights even if the model for some reason doesn't have the scaled_fp8 key 2025-10-21 19:40:50 +03:00
kijai 200f6943e3 Add sageattn mode that allows torch.compile 
Latest wheel from woct0rdho includes the torch.compile fix:

https://github.com/woct0rdho/SageAttention/releases

Based on my quick testing this reduces peak VRAM usage a bit when running sageattn + torch.compile
 2025-10-20 15:16:43 +03:00
kijai 8081e1337c Fix downcasting for fp8_fast and add error to indicate you can't do scaled downcast currently 2025-10-20 13:46:05 +03:00
kijai 9ecb80a58b Support loading VACE LoRAs (for ditto) 2025-10-20 11:49:49 +03:00
kijai 99c0efdb45 Expose force_parameter_static_shapes in torch.compile options 2025-10-19 18:01:03 +03:00
kijai c876108059 Update fp8_e4m3fn compile warning on older arch to indicate it should now work with latest Triton 
https://github.com/woct0rdho/triton-windows/releases/tag/v3.5.0-windows.post21
 2025-10-16 13:08:42 +03:00
kijai bb75cddd60 Add minimal FlashVSR upscale support 
https://zhuang2002.github.io/FlashVSR/

This only implements the projection model and the VAE, which seems to be enough for upscaling. This does NOT implement any of the streaming and sparse attention code.
 2025-10-15 18:24:28 +03:00
kijai 139bdf827f Squashed commit of the following: 
commit 73dd1a06d33953912f5dd684f168028b14e42a36
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Oct 13 19:47:38 2025 +0300

    cleanup

commit 39bc2cecf493e2eb176b55e8841d933f0da1ec39
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Oct 13 19:24:20 2025 +0300

    Allow scheduling ovi cfg

commit 2c153c5f324dbd59670ad9c51a7995459504a3cd
Merge: dba7667 32eb6b4
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Oct 13 17:48:20 2025 +0300

    Merge branch 'main' into ovi

commit dba76674c71af7bf94c82834a0b0e40d94043c99
Merge: 0f11a43 5a0456e
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sun Oct 12 22:45:43 2025 +0300

    Merge branch 'main' into ovi

commit 0f11a439622799ad8070f8a2b8cc8e6a041b761d
Merge: 0999f50 e2d8c9b
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Oct 11 07:48:06 2025 +0300

    Merge branch 'main' into ovi

commit 0999f50cfe025290cd7ce88a8dd1acff0b38d9bd
Merge: d45df1f f1d1c83
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Fri Oct 10 22:16:09 2025 +0300

    Merge branch 'main' into ovi

commit d45df1fb5b7c629b15eabc197357d62bdc232aaf
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Oct 9 20:21:37 2025 +0300

    Remove dependency for librosa

commit d8e7533fdf7eab1d2489c3e025a908c02d997444
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Oct 9 19:57:28 2025 +0300

    Remove omegaconf dependency

commit f4e27ff018e98cb5b09655dceda399baea36b240
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Oct 9 19:31:06 2025 +0300

    Fix VACE

commit 35d3df39294831e5e7568b6f7e16d2ecf2d790a0
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Oct 9 00:26:40 2025 +0300

    small update

commit 96f8ea1d26869ab7e49e12a07f19d5d5a2023253
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 22:32:57 2025 +0300

    Create wanvideo_2_2_5B_ovi_testing.json

commit a2511be73b9da7019fd21aeb0b521af941c09150
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 22:32:54 2025 +0300

    Update nodes_sampler.py

commit d3688b8db71452ea1f7c9a2bc0216441d524e56c
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 21:43:02 2025 +0300

    Allow EasyCache to work with ovi

commit 586d9148a0306ef5d30e9a971a9c3be4cd3ecc97
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 19:09:06 2025 +0300

    Update model.py

commit 61eedd2839decdb7d4c2ddd5f1310fdaf49d36ad
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 19:09:02 2025 +0300

    I2V fix

commit a97fcb1b9ae9fb7bbfdf668c24816e014a1b58d1
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 17:57:28 2025 +0300

    Add nodes to set audio latent size

commit d41e42a697f3d561dabbc22566f633b5f1bbd952
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 16:42:04 2025 +0300

    Support loading mmaudio vae from .safetensors

commit 1b0e28ec41e3c97fe1f2f057fef9b9bbcb87bca7
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 16:19:53 2025 +0300

    Update nodes_sampler.py

commit fbd18f45fe85ede8edcb5aebaea7ceb5b6eab5a2
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 10:16:44 2025 +0300

    Fixes for other workflows

commit b06993b637198f7fad92208f3b3dc9a7d7f57c7f
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Wed Oct 8 09:46:27 2025 +0300

    initial commit

    T2V works
 2025-10-13 20:16:53 +03:00
kijai e2d8c9bef5 Allow using tiny vae in other precisions 
The model is available in fp16 only though
 2025-10-11 07:47:52 +03:00
kijai 6075807e03 Fix for some fp8_scaled models 2025-10-07 13:30:41 +03:00
kijai bb23263f78 Separate full model's ip and ref layer loading 
Allows using full ref with lite ip adapter, or full ref alone without loading the ip weights
 2025-10-06 18:42:14 +03:00
kijai c517cfbc17 Merge branch 'main' into lynx 2025-10-06 13:02:23 +03:00
kijai d20d271a24 Update nodes_model_loading.py 2025-10-05 12:19:43 +03:00
kijai 71c8a4961b Merge branch 'pr/1240' 2025-10-03 19:24:40 +03:00
kijai 28ae01e11b fixes 2025-10-01 10:05:29 +03:00
kijai 0ed0f54d11 initial lynx full support 2025-09-28 02:01:01 +03:00
kijai 4ba6c88ad8 Update nodes_model_loading.py 2025-09-27 16:11:07 +03:00
kijai 358baa2c2a Lynx + VACE 2025-09-27 02:05:17 +03:00
kijai ab31158673 init: support lite model 2025-09-27 00:49:02 +03:00
kijai 37365817e8 Revert unicode character in warning strings 
Seems it may cause issues on some systems
 2025-09-26 12:39:39 +03:00
kijai 86193e3cc9 Add a warning for possible custom node version conflict from having multiple WanVideoWrappers installed 2025-09-26 01:01:25 +03:00
kijai b8c2bb0a93 Add torch native RMSNorm as a choice 2025-09-23 17:41:24 +03:00
kijai 2c4dfaf4c8 WanAnimate: Fix regression in image quality when using fp8 
Face blocks not doing well in fp8
 2025-09-22 03:12:48 +03:00
kijai 02583db554 WanAnimate: Encode pose latents in the loop too for better sync and seams between windows 2025-09-22 02:36:17 +03:00
kijai fc3a684b0b WanAnimate: Move face adapter blocks to corresponding main blocks to include them in block swap 2025-09-21 16:34:17 +03:00
kijai e4627466f5 WanAnimate block swap fix 2025-09-19 16:59:57 +03:00
kijai b06562823b Fix GGUF with WanAnimate 2025-09-19 11:35:14 +03:00
kijai 79583d4be3 Support WanAnimate 2025-09-19 10:14:08 +03:00
kabachuha 7eafe77ba0 update magcache ratios 2025-09-16 21:07:39 +03:00
kijai 076c4a5c7e Experimental: Allow HuMo to work with InfiniteTalk 
Doesn't work that great, but pushing this anyway for possible future usecases
 2025-09-15 19:07:34 +03:00
kijai 38fd791a77 Squashed commit of the following: 
commit fda0fe6e0c21eb10276ae302cd88b6cbcf5b36b5
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 16:55:00 2025 +0300

    Create wanvideo_HuMo_example_01.json

commit cffe3039c3d2fbacd4803329bf31b5fdc45215ba
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 16:30:49 2025 +0300

    Update model.py

commit ddce018a5a6ffeb926860342889b12efb7343ec0
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 16:29:27 2025 +0300

    cleanup

commit 8c021b8b3f66144804e500e74aa6f2be52f9f9fc
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 16:23:27 2025 +0300

    avoid compile graph break

commit ef9c7732042261581b4bba6d980def78633f56dc
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 16:16:13 2025 +0300

    Allow using whisper model without decoder layers

commit 8d0ba29ee84d14be6084ecbcee1cbc9414128fb3
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 15:55:26 2025 +0300

    start/end percent for HuMo audio

commit bfe0d358a8820240f262351e61cfb979cb9a47ff
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 15:37:11 2025 +0300

    cleanup

commit e563ae317f24a7f5751b43cdef4bffbaeaea5114
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Sep 13 14:02:21 2025 +0300

    Make audio work

commit 95855196c51b1124a19079b746c5d12ec70d9026
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Fri Sep 12 18:10:04 2025 +0300

    cfg

commit d5a18b090fe719b7f0b00a0f68e6824685598313
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Fri Sep 12 03:10:15 2025 +0300

    wrong way around

commit 34c8c4842c14002fe4694dfa23c24a65b7ea39d0
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Fri Sep 12 03:01:45 2025 +0300

    Update nodes.py

commit 47d1e2ab5f3e1483782d0739f5b51cdd33707c36
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Fri Sep 12 02:47:03 2025 +0300

    update

    image inputs are working but audio still doesn't do anything

commit 67890d816a64459944091cb01478c1e0ec4c4a82
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Sep 11 21:13:12 2025 +0300

    update

commit dbcef53405bb78feae4c5d2c6b310b76e4ef9949
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Sep 11 17:09:37 2025 +0300

    Update model.py

commit 92c9aac51f4d37988757510a4e57179834cc5de2
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Thu Sep 11 16:15:39 2025 +0300

    init

    untested as no weights released as of yet
 2025-09-13 16:55:28 +03:00
kijai 57586bed1d Error when trying to use GGUF extra model with non-GGUF main model 2025-09-13 10:34:34 +03:00
kijai 617f89e0f5 Allow WanVideoExtraModelSelect to see GGUF files too 2025-09-12 11:40:41 +03:00
kijai ae768f53a4 Make merge_lora switches with multiple loras behave like it used to and how the tooltip indicates 2025-09-06 19:28:16 +03:00
kijai 488b6628c7 typo 2025-09-03 22:47:42 +03:00
kijai 8131eaef23 update tooltip 2025-09-03 22:26:07 +03:00
kijai 24ec3f6960 Add WanVideoLoraSelectByName 
select lora by name string
 2025-09-03 20:22:41 +03:00
kijai 54391300b1 Never use main_device with unmerged loras 2025-09-03 10:00:51 +03:00
kijai c57ffd8150 update example 2025-09-03 00:41:23 +03:00
kijai 42d7180759 keep scale_weight on gpu to avoid needless casts 2025-09-02 01:04:16 +03:00
kijai b8acd3ee48 Allow using fp16 multitalk model with GGUF again 2025-08-31 18:57:59 +03:00
kijai b9b46638ac Fix FantasyPortrait + GGUF main model 2025-08-31 18:41:08 +03:00
kijai b1c8b8a280 remove flex attention as redundant 2025-08-31 18:14:38 +03:00
kijai 7dd0e1ac61 Update nodes_model_loading.py 2025-08-29 21:21:24 +03:00
kijai 3a290cfd15 Update nodes_model_loading.py 2025-08-29 20:41:40 +03:00
kijai 6a2053c9d1 Update nodes_model_loading.py 2025-08-29 15:26:47 +03:00
kijai 6faa24b7f2 Implement Framepack long geneneration method 
RoPE handling is comfyanon's code
 2025-08-28 18:48:39 +03:00
kijai a5621b8739 Add pose input 2025-08-27 22:43:28 +03:00
kijai c89b82e479 Merge branch 'main' into s2v 2025-08-27 12:24:08 +03:00
kijai e241998f53 Fix Uni3C 2025-08-27 12:21:25 +03:00