kijai
b748ed8bdd
Squashed commit of the following:
...
commit f06ce25f6c50174b0e7b12c3517827a6650f33fa
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Aug 17 13:10:02 2025 +0300
redundant
commit 9957f765e48f68b21713c33db334231207107b01
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Aug 17 12:57:12 2025 +0300
Update nodes.py
commit 9797f15ed1e5a9b9b93f777e92cd82ed584c2b57
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Aug 17 12:35:46 2025 +0300
Remove the "FM" scheduler
This is just dpm++
commit 244fc2b125253a4c7b6e91ca8dd0b4dc8564c2f0
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Aug 17 02:05:26 2025 +0300
just use default rope I guess...
commit 5c3a60d3b189864f8f2f0977a552499b202326ba
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Aug 17 01:35:49 2025 +0300
Update nodes.py
commit ee47ed17c086f8468fd5a256318274c0077f6dfc
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sun Aug 17 01:35:36 2025 +0300
Update model.py
commit 8a17ee7d41ae5789b8d7ed01eb8b48c0c3b52ce7
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Sat Aug 16 23:20:10 2025 +0300
init
2025-08-17 13:51:23 +03:00
kijai
d6ac1842fa
remove print
2025-08-17 01:41:49 +03:00
kijai
f2fd411a7b
Add option for manually setting rope offset for Stand-In reference
...
Experimental
2025-08-15 10:18:00 +03:00
kijai
5e7c89bd00
Update wan_video_vae.py
2025-08-14 19:01:02 +03:00
kijai
0c4426fc2b
FantasyPortrait reqs and cleanup
...
unsure if I want to add onnx in the requirements at this stage...
2025-08-14 18:53:08 +03:00
kijai
24683f1dad
Squashed commit of the following:
...
commit 6a01a8a1d80d36b5b8ac979a36069c8eb0c2f9a7
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 15:40:50 2025 +0300
Update wanvideo_2_1_I2V_FantasyPortrait_example_01.json
commit e3cf4bf5bc13321e6d8f91fcb7ee92210a7adf01
Merge: bbf14ec f3d5f6b
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 15:08:53 2025 +0300
Merge branch 'main' into fantasy_portrait
commit bbf14ec9e9965c1a8582eea02b50913e79a036d0
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 02:16:11 2025 +0300
update
commit 8192f9f4302b3933e48641a8ef313929e3e263aa
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 01:46:15 2025 +0300
progress bar, fix context windows
commit 39fab8ad4d950a974ba49bd177814f30f518b478
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 01:29:15 2025 +0300
Update nodes.py
commit 36f472c0134e6342ab8c2062a7e3f0b0c829003b
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 01:14:24 2025 +0300
Add start/end percent
commit 16f5922c6bc575754412c9b473907377562b956c
Author: kijai <40791699+kijai@users.noreply.github.com >
Date: Thu Aug 14 00:58:57 2025 +0300
init
2025-08-14 15:41:25 +03:00
kijai
f3d5f6b3ab
allow stand-in to work with chunked rope
2025-08-14 14:12:06 +03:00
kijai
e1c052ff43
Update attention.py
2025-08-14 00:11:02 +03:00
kijai
8db5521463
Possible bandaid for q k v dtype mismatch
...
Still no clue where or why it happens, but clearly is happening for some when using sage with Stand-In
2025-08-14 00:10:38 +03:00
kijai
b08f10ffd8
Re-implement Stand-in kv_cache
2025-08-13 11:58:22 +03:00
kijai
d596901055
Allow stand-in with VACE
...
Don't know how well it can actually work, has some effect
2025-08-13 10:00:37 +03:00
kijai
083237051f
I suppose kv_cache isn't actually used for this...
2025-08-13 00:07:14 +03:00
kijai
8319c961c0
Update model.py
2025-08-12 22:10:57 +03:00
kijai
06863fe2d2
Allow doing T2V with the I2V encode node when no images are connected and allow using native set latent noise mask -node
...
Latent masking still doesn't work properly
2025-08-12 11:47:33 +03:00
Jukka Seppänen
bf84e99dec
Merge pull request #1019 from UaRuairc/patch-1
...
Fix res_multistep.step to set sigma_next correctly when ending early
2025-08-11 16:24:38 +03:00
kijai
057ee642f6
Add async prefetch as option for block swapping
...
Can speed up block swapping on some systems, added debug option as well so you can see if enabling the option gives you any benefit.
2025-08-11 16:17:16 +03:00
FB
1e091d181b
Fix res_multistep.step to set sigma_next correctly when ending early
...
Use the next sigma from the schedule when sampler ends early, only assume `sigma_next = 0` when on the true final step.
2025-08-11 14:17:08 +01:00
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