nodes/kijai-ComfyUI-WanVideoWrapper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,410 Commits 8 Branches 0 Tags
b99eac73da2178cdc524a3a9628ae6e53681b4d1
Commit Graph
26 Commits
Author SHA1 Message Date
kijai 5360eeb345 Squashed commit of the following: 
commit fd32b14fdc
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Tue Dec 23 02:02:31 2025 +0200

    Clean prints

commit 1776695e26
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Tue Dec 23 01:48:12 2025 +0200

    Update nodes_model_loading.py

commit ef36204fa8
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Tue Dec 23 01:35:08 2025 +0200

    Reduce peak VRAM use

commit c6f32c1424
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Dec 22 23:53:41 2025 +0200

    Norm dtype

commit 6d4a0f6e53
Merge: e7e0006 3e45021
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Dec 22 22:11:38 2025 +0200

    Merge branch 'main' into longcat_avatar

commit e7e00061e5
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Dec 22 00:43:01 2025 +0200

    Update nodes_sampler.py

commit eb5ec262a0
Merge: 7c0ba84 fed3b22
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Mon Dec 22 00:42:53 2025 +0200

    Merge branch 'main' into longcat_avatar

commit 7c0ba84a26
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sun Dec 21 23:00:43 2025 +0200

    remove prints

commit 06a86923e7
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sun Dec 21 22:53:25 2025 +0200

    Fix ref latent

    oops

commit dca3106f10
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Dec 20 18:46:32 2025 +0200

    Expose more options, make vid2vid easier

commit 175418b8d2
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Dec 20 03:15:24 2025 +0200

    Create LongCatAvatar_testing_wip.json

commit 4a6e2d3c6c
Author: kijai <40791699+kijai@users.noreply.github.com>
Date:   Sat Dec 20 03:14:49 2025 +0200

    Init
 2025-12-23 12:17:07 +02:00
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 699bad3887 InfiniteTalk: Don't stack or return frames when using output path 2025-09-13 20:10:13 +03:00
kijai fe379fa77f InfiniteTalk: Add option to save results during the process, make it clearer no latents are returned 2025-09-08 18:50:53 +03:00
kijai 011c0ce38d InfiniteTalk: Pad with silent embeds instead of repeat, add MultiTalkSilentEmbeds -node 2025-09-06 21:58:03 +03:00
kijai 26a11c3044 Update nodes.py 2025-08-31 18:01:53 +03:00
kijai 5f5f8ae30a Merge branch 'main' into dev 2025-08-26 00:33:49 +03:00
kijai efcef40b00 fix name 2025-08-26 00:18:05 +03:00
kijai 6fce0e2d3b Add Wav2VecModelLoader to load wav2vec2 from single .safetensors 
https://huggingface.co/Kijai/wav2vec2_safetensors/
 2025-08-26 00:09:46 +03:00
kijai d9def84332 Fix UniAnimate and MultiTalk loading 2025-08-25 14:09:08 +03:00
kijai 66d4c5b90d Slice possible alpha channel away before encoding 2025-08-25 12:50:41 +03:00
kijai 9a2a13498a Cleanup MultiTalk model code 2025-08-23 17:49:04 +03:00
kijai 70bced06f4 Return exact audio frame count if num_frames above it 2025-08-20 21:08:25 +03:00
kijai 8b4546896e Update nodes.py 2025-08-20 13:39:46 +03:00
kijai a1220f7f36 Handle InfiniteTalk first frame when not using the looping sampling 2025-08-20 13:33:44 +03:00
kijai 04a99fd4e2 Add tooltips 2025-08-19 20:19:01 +03:00
kijai b6d4c172f0 Allow using GGUF Multi/InfiniteTalk models 2025-08-19 17:48:58 +03:00
kijai e0eee40bde Add InfiniteTalk loop method 2025-08-19 10:45:42 +03:00
kijai 4b4a3b4f8f Update nodes.py 2025-08-17 10:55:06 +03:00
kijai 70e3c6b524 update 2025-07-03 21:41:44 +03:00
kijaiandRudra-ai-coder 475f371016 Multiple talkers 
Initial commit, works but needs more utility for the mask creation.

Based mostly on Rudra-ai-coder's modifications.

Co-Authored-By: Rudra-ai-coder <177262225+rudra-ai-coder@users.noreply.github.com>
 2025-07-03 19:03:12 +03:00
kijai 0a11c67a0c MultiTalk sampling 
New node (WanVideoImageToVideoMultiTalk) that also enables the continuous sampling method from the original code. Compared to context windows this works better for shorter clips, but degrades longer it goes.
 2025-07-02 16:18:04 +03:00
kijai 09b4c3a865 support context windows, torch compile fixes 2025-06-19 20:29:32 +03:00
kijai f3614e6720 Update nodes.py 2025-06-19 00:56:36 +03:00
kijai 1fe72d27aa loudness norm 2025-06-18 18:35:06 +03:00
kijai 58104b620f init 2025-06-18 15:41:53 +03:00