kijai
5da8a6b169
Fix MultiTalk on some models
2025-10-31 16:50:00 +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
42df277488
Merge branch 'main' into dev
2025-08-25 12:51:46 +03:00
kijai
66d4c5b90d
Slice possible alpha channel away before encoding
2025-08-25 12:50:41 +03:00
kijai
11f3e41e9a
Merge branch 'main' into dev
2025-08-23 21:00:45 +03:00
kijai
9a2a13498a
Cleanup MultiTalk model code
2025-08-23 17:49:04 +03:00
kijai
b4d2290859
Merge branch 'main' into dev
2025-08-21 18:42:47 +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
2a0bd1c42d
Merge branch 'main' into dev
2025-08-19 18:06:49 +03:00
kijai
b6d4c172f0
Allow using GGUF Multi/InfiniteTalk models
2025-08-19 17:48:58 +03:00
kijai
e2a5fe8b4b
Merge branch 'main' into dev
2025-08-19 11:51:08 +03:00
kijai
e0eee40bde
Add InfiniteTalk loop method
2025-08-19 10:45:42 +03:00
kijai
e4f422cf99
Update multitalk.py
2025-08-17 19:33:20 +03:00
kijai
497fafe2ea
Merge branch 'main' into dev
2025-08-17 19:23:34 +03:00
kijai
427e7be6c2
fix multitalk
2025-08-17 18:24:48 +03:00
kijai
1d7e0848e0
Allow Phantom to work with MultiTalk
2025-08-17 16:46:50 +03:00
kijai
9a7dba06c1
Update multitalk.py
2025-08-17 16:43:46 +03:00
kijai
be285f5258
multitalk fix
2025-08-17 15:14:27 +03:00
kijai
4b4a3b4f8f
Update nodes.py
2025-08-17 10:55:06 +03:00
kijai
d6bee68845
Update multitalk.py
2025-08-15 12:24:37 +03:00
kijai
e1f5d185ee
Use original Multitalk attention code with exactly 2 speakers
2025-07-14 17:06:48 +03:00
kijai
70e3c6b524
update
2025-07-03 21:41:44 +03:00
kijai and Rudra-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
49430f900b
Fix for transformers 4.53.0
2025-07-01 12:00:28 +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
kijai