 kijai
|
4a41fb0aaf
|
cleanup experimental context window stuff
Didn't really work anyway
|
2025-04-29 17:36:07 +03:00 |
|
|
kijai
|
b78505014c
|
Fix Phantom and FantasyTalking when not using TeaCache
|
2025-04-29 10:31:52 +03:00 |
|
|
kijai
|
e8074288df
|
Update wanvideo_I2V_FantasyTalking_example_01.json
|
2025-04-29 09:58:12 +03:00 |
|
|
kijai
|
e3afc7fc75
|
Add helper node for cfg scheduling and allow scheduling audio_cfg as well
|
2025-04-29 09:00:01 +03:00 |
|
|
kijai
|
1b3592f6b4
|
Update nodes.py
|
2025-04-29 07:34:36 +03:00 |
|
|
kijai
|
ed068e1fe3
|
Fix lowvram lora load when not using quantization
|
2025-04-29 02:21:11 +03:00 |
|
|
kijai
|
fe25d21fba
|
Fix audio cfg
silly mistake
|
2025-04-29 02:07:05 +03:00 |
|
|
kijai
|
2d0e0fe698
|
Update wanvideo_I2V_FantasyTalking_example_01.json
|
2025-04-29 01:46:53 +03:00 |
|
|
kijai
|
ca0974d5f0
|
cleanup
|
2025-04-29 01:46:39 +03:00 |
|
|
kijai
|
a9ec21bb8f
|
Update wanvideo_I2V_FantasyTalking_example_01.json
|
2025-04-29 00:19:59 +03:00 |
|
|
kijai
|
a7fa683c2c
|
Update wanvideo_I2V_FantasyTalking_example_01.json
|
2025-04-29 00:07:25 +03:00 |
|
|
kijai
|
1f6fd1e5a8
|
Don't download redundant wave2vec model files.
.bin and .h5 can be safely deleted
|
2025-04-28 23:24:01 +03:00 |
|
|
kijai
|
e334f78124
|
Update nodes.py
|
2025-04-28 21:50:57 +03:00 |
|
|
kijai
|
c8a084d27a
|
Update nodes.py
|
2025-04-28 21:37:48 +03:00 |
|
|
kijai
|
8117c6f033
|
Context windows with FantasyTalking
|
2025-04-28 20:24:41 +03:00 |
|
|
kijai
|
d96787b312
|
Update wanvideo_I2V_FantasyTalking_example_01.json
|
2025-04-28 19:27:49 +03:00 |
|
|
kijai
|
4e562b5d92
|
Add FantasyTalking example
|
2025-04-28 19:14:03 +03:00 |
|
|
kijai
|
5683d8306a
|
Support FantasyTalking
|
2025-04-28 19:10:32 +03:00 |
|
|
kijai
|
df95c85283
|
Fix sageattn when using fp32
|
2025-04-27 17:31:06 +03:00 |
|
|
kijai
|
4fc4159c88
|
fix up default rope dtype
|
2025-04-27 17:22:02 +03:00 |
|
|
kijai
|
fc7ab666a2
|
support loading Fun camera model
Input not functional yet
|
2025-04-25 17:02:10 +03:00 |
|
|
kijai
|
caebbafab8
|
version after merge
|
2025-04-25 16:21:19 +03:00 |
|
|
kijai
|
03eeef32a3
|
Merge branch 'dev'
|
2025-04-25 16:20:59 +03:00 |
|
|
kijai
|
c09b981d1e
|
version
|
2025-04-25 16:20:50 +03:00 |
|
|
kijai
|
e75e6d6933
|
Update nodes.py
|
2025-04-25 16:19:52 +03:00 |
|
|
kijai
|
031d8ac817
|
disable enhance always with DF
|
2025-04-25 15:47:25 +03:00 |
|
|
kijai
|
33b8f1c082
|
Support Fun control 1.1
Supports the new reference image input to the 1.1 control model
|
2025-04-25 15:44:18 +03:00 |
|
|
kijai
|
863829d083
|
dtype fixes and maybe allow fp8_fast to work
Unsure when this has changed but seems that _scaled_mm now works with same dtype? This fixes the quality degradation of fp8_fast in initial tests.
|
2025-04-25 03:12:10 +03:00 |
|
|
kijai
|
c7b2635f01
|
Update model.py
|
2025-04-23 20:37:48 +03:00 |
|
|
kijai
|
96a2172e13
|
Phantom + VACE testing
|
2025-04-23 20:34:28 +03:00 |
|
|
kijai
|
b3f3b0cd93
|
Update model.py
|
2025-04-23 20:11:08 +03:00 |
|
|
kijai
|
4602b9c885
|
Fix phantom start percent
|
2025-04-23 10:30:33 +03:00 |
|
|
kijai
|
e0e5fcf713
|
Add start/end percent for Phantom and other small fixes
|
2025-04-23 01:00:41 +03:00 |
|
|
kijai
|
2b0bf44994
|
Update wanvideo_phantom_subject2vid_example_01.json
|
2025-04-22 22:42:58 +03:00 |
|
|
kijai
|
24876cffc1
|
Update nodes.py
|
2025-04-22 22:34:45 +03:00 |
|
|
kijai
|
1f53574387
|
Create wanvideo_phantom_subject2vid_example_01.json
|
2025-04-22 21:15:54 +03:00 |
|
|
kijai
|
6fadcbd957
|
Support Phantom, refactor model dtypes, reduce DF model memory use
|
2025-04-22 21:13:27 +03:00 |
|
|
kijai
|
a623f87dca
|
Update wanvideo_skyreels_diffusion_forcing_extension_example_01.json
|
2025-04-22 16:05:26 +03:00 |
|
|
kijai
|
6099ad393b
|
Update wanvideo_skyreels_diffusion_forcing_extension_example_01.json
|
2025-04-22 10:24:26 +03:00 |
|
|
kijai
|
949c887e0c
|
Fix FLF2V when using vram management node
|
2025-04-22 09:44:46 +03:00 |
|
|
kijai
|
5109a74839
|
Update wanvideo_skyreels_diffusion_forcing_extension_example_01.json
|
2025-04-22 08:13:26 +03:00 |
|
|
kijai
|
6ba7bc811e
|
Update nodes.py
|
2025-04-22 02:05:08 +03:00 |
|
|
kijai
|
f93e54d21b
|
Allow unianimate with DF
|
2025-04-22 01:01:22 +03:00 |
|
|
kijai
|
3ae0bc1fec
|
Create wanvideo_skyreels_diffusion_forcing_extension_example_01.json
|
2025-04-22 00:29:57 +03:00 |
|
|
kijai
|
e3ea2bf392
|
Allow VACE with DF
|
2025-04-21 20:01:20 +03:00 |
|
|
kijai
|
884069121f
|
Fix latent preview fallback if disabled
|
2025-04-21 19:11:16 +03:00 |
|
|
kijai
|
f371c0a736
|
Allow TeaCache for DF
Guess it works
|
2025-04-21 18:30:40 +03:00 |
|
|
kijai
|
65f5505fca
|
Initial Skyreels DiffusionForcing model support
On it's own sampler at least for now while I figure out how it all works.
|
2025-04-21 18:13:51 +03:00 |
|
|
kijai
|
e5a326c981
|
Use penultimate_hidden_states instead when using native clip vision
The new Skyreels 1.3B I2V did not work otherwise, this seems to make it match the wrapper clip vision output better
|
2025-04-21 01:33:51 +03:00 |
|
|
kijai
|
7d005201a2
|
Allow loading UniAnimate LoRA with low vram load as well
|
2025-04-20 18:05:43 +03:00 |
|