kijai
ab06ac2f64
Closer to original EchoShot implementation, bugfixes
...
Turns out I never had the right way of using EchoShot and was always just accidentally using my existing rope splitting... which just worked with the EchoShot weights, this commit adds proper EchoShot and it's used when their prompt format is used, the previous behaviour can be restored by using my splitting method with " | " between the prompts. EchoShot example has been updated to reflect that.
2025-08-07 12:08:42 +03:00
kijai
801f543a7a
Allow LoRA timestep scheduling
...
LoRA strength can now be a list of floats that represents the strength at any given step
2025-08-04 00:02:19 +03:00
kijai
9edab74562
Default non_blocking to False
...
too many RAM issues
2025-08-01 02:29:07 +03:00
kijai
b60814fb6b
Fix split prompting, get rid of diffusers on model class
2025-07-31 15:11:47 +03:00
kijai
f835baa3d3
fix riflex
2025-07-29 10:52:39 +03:00
kijai
d6e9af7090
2.2 stuff
2025-07-28 21:38:40 +03:00
kijai
cb36e1013e
Fix
2025-07-26 19:01:58 +03:00
kijai
df1476bf42
Support EchoShot
...
https://github.com/D2I-ai/EchoShot
2025-07-26 18:51:29 +03:00
kijai
a35eb7dfa4
Basic sageattn3 support
...
Probably going to need further timestep scheduling as the quality of sage3 on it's own is pretty bad.
2025-07-25 20:48:34 +03:00
kijai
66226a8a1b
why was this ever this way...
2025-07-23 17:17:27 +03:00
kijai
6ef9224dfe
Update model.py
2025-07-21 13:51:33 +03:00
kijai
feddafcea2
Update model.py
2025-07-18 18:52:32 +03:00
kijai
6b9565ed63
Code refactoring
2025-07-18 16:15:50 +03:00
kijai
0e920e5b18
support VACE
2025-07-18 14:04:04 +03:00
kijai
55fc8a13e0
better mask cache, optimize
2025-07-18 13:55:06 +03:00
kijai
a7166fc1a4
fix and rename args to be clearer
2025-07-18 01:28:01 +03:00
kijai
712eecf64b
more compile friendly
2025-07-18 00:53:12 +03:00
kijai
605011a237
allow setting dense attention mode
2025-07-17 23:47:08 +03:00
kijai
9039d95721
cleanup and optimize
2025-07-17 22:40:26 +03:00
kijai
7c8020f8e8
works but slow
2025-07-17 21:49:14 +03:00
kijai
6ee7ad508e
init (not working)
2025-07-17 20:47:02 +03:00
kijai
2263d02a0a
basic Pusa support
2025-07-17 10:06:01 +03:00
kijai
24d3de2126
Add EasyCache
2025-07-14 17:27:10 +03:00
kijai
365a1ce1d6
more chunking and refactoring
2025-07-12 20:18:52 +03:00
kijai
895c92febd
Update model.py
2025-07-12 03:04:46 +03:00
kijai
039b211ef7
cleanup
2025-07-12 02:06:02 +03:00
kijai
127bfa2c99
refactor self attention
2025-07-11 23:00:59 +03:00
kijai
15f0e62e5f
Add chunked RoPE option to reduce peak VRAM usage when not using torch.compile
2025-07-10 17:15:06 +03:00
kijai
a9ba0e1cb4
small possible optimizations
2025-07-10 14:18:04 +03:00
kijai
d903ea7d3d
small fixes, add comfy pbar for model loading
2025-07-06 23:55:37 +03:00
kijai
6ae5531bad
Basic GGUF support (yes, really)
2025-07-06 21:37:45 +03:00
kijai
974dd656da
some offloading for multitalk
2025-07-03 21:56:19 +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
f621d2a5fc
Update model.py
2025-06-30 20:31:39 +03:00
kijai
2da36b7fda
context window progress bar
...
better than nothing, and allow cancelling mid context
2025-06-20 17:29:27 +03:00
kijai
157fbb1b7f
Merge branch 'main' into multitalk
2025-06-20 13:53:31 +03:00
kijai
8387a64b15
bump version
2025-06-20 10:57:13 +03:00
kijai
09b4c3a865
support context windows, torch compile fixes
2025-06-19 20:29:32 +03:00
kijai
b5cae8bf1a
Fix FLF2V model
2025-06-18 15:49:01 +03:00
kijai
58104b620f
init
2025-06-18 15:41:53 +03:00
kijai
b322192d93
Support minimaxremover
...
https://minimax-remover.github.io/
2025-06-17 09:45:12 +03:00
kijai
ad43eed0d0
Add MagCache and consolidate cache_args to support both
...
Not really getting great results yet with MagCache, but at least pretty much on bar with TeaCache so it can be an option that hopefully improves in time
2025-06-13 12:31:13 +03:00
kijai
e7c39757f6
Allow compiling crossattn
...
I don't remember why I even disabled this... seems to work, big effect with NAG
2025-06-12 19:04:15 +03:00
kijai
d34cabc985
Cleanup, create own node for NAG
2025-06-12 18:18:28 +03:00
kijai
23796233df
Some fixes and adjustments
2025-06-12 17:26:54 +03:00
kabachuha
803ba1cd72
rm commented out code
2025-06-12 15:34:11 +03:00
kabachuha
e8d3f1cca5
fixup when context lens are none
2025-06-12 15:30:30 +03:00
kabachuha
bdf7a3d02a
pass nag scale into the model
2025-06-12 15:26:59 +03:00
kabachuha
0ac366ba03
add nag to attention internal parts
2025-06-12 14:43:51 +03:00
kijai
a290f75b5e
Update model.py
2025-06-05 23:41:17 +03:00
kijai