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
2a21c4f6ae
VAE cleanup and adjustments, add node to allow using native VAE
2025-08-06 17:28:50 +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
5406a72f62
Improve text encoder cache and add alternative node which leaves nothing to memory after encoding
...
WanVideoTextEncodeCached -node will load T5 when the prompt is not found in the cache, then unload it completely.
2025-08-01 12:36:19 +03:00
kijai
9edab74562
Default non_blocking to False
...
too many RAM issues
2025-08-01 02:29:07 +03:00
kijai
945700d56e
5B fixes
2025-07-31 22:41:56 +03:00
kijai
b60814fb6b
Fix split prompting, get rid of diffusers on model class
2025-07-31 15:11:47 +03:00
kijai
9a5d752ba1
Support custom sigmas on more schedulers
2025-07-30 16:20:48 +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
3659c3f6e6
Progress bar for text encoding
2025-07-28 10:00:17 +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
729b6fdf7c
support sparse sageattn2 for radial attn
...
Needs this installed:
https://github.com/Radioheading/Block-Sparse-SageAttention-2.0
2025-07-23 00:27:14 +03:00
kijai
6ef9224dfe
Update model.py
2025-07-21 13:51:33 +03:00
kijai
59add151eb
Update attention.py
2025-07-20 16:22:27 +03:00
kijai
768a4b2d90
Fix radial attention cache not resetting on resolution change, add more robust supported dimension check
2025-07-20 12:15:01 +03:00
kijai
9f75b7e051
Fix tiled_vae + endframe
2025-07-20 02:33:24 +03:00
kijai
1f25bba463
Merge branch 'pr/828'
2025-07-20 02:13:26 +03:00
kijai
edd9b20691
Add res_multistep
2025-07-20 01:41:17 +03:00
komikndr
d3aba90119
adding 64 block_size
2025-07-19 20:05:19 +07:00
kijai
feddafcea2
Update model.py
2025-07-18 18:52:32 +03:00
kijai
5a305a7f9f
include sparse_sage_API code
...
https://github.com/jt-zhang/Sparse_SageAttention_API
2025-07-18 17:16:43 +03:00
kijai
6b9565ed63
Code refactoring
2025-07-18 16:15:50 +03:00
kijai
a1cc320c36
force using the set node
2025-07-18 14:26:45 +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
8919e65bab
cache the mask
2025-07-18 01:43:45 +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
6bc53b771d
refactor scheduler import
2025-07-17 15:56:55 +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
490b0a8ead
better context window progress bar, add VAE decode progress bar
2025-07-04 20:00:03 +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