kijai
e21fe20a4d
Support SkyReels TalkingAvatar (A2V)
2026-01-31 23:24:29 +02:00
kijai
8640bfad52
VRAM optimizations
...
Minor for almost everything, major for multitalk when using masks
2026-01-22 19:46:52 +02:00
kijai
5da8a6b169
Fix MultiTalk on some models
2025-10-31 16:50:00 +02:00
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
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
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
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 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
09b4c3a865
support context windows, torch compile fixes
2025-06-19 20:29:32 +03:00
kijai
58104b620f
init
2025-06-18 15:41:53 +03:00
kijai