kijai
b4dc58fd9f
Split cross attention when using multiple prompts and/or clip image embeds
...
Allows for (pretty weak) prompt travel and may help with the endframe workflow.
2025-03-25 00:07:41 +02:00
kijai
4b8672ac3b
Update model.py
2025-03-23 02:39:34 +02:00
kijai
8fbf92ae93
Improved loop stitching on decode
2025-03-22 23:05:32 +02:00
kijai
309240c0f4
fix T2V (again)
2025-03-22 10:14:07 +02:00
kijai
2863956da7
workflow updates
2025-03-22 02:45:11 +02:00
kijai
b415fe78f1
fix T2V
2025-03-21 20:44:54 +02:00
kijai
c3e96fd6f9
Experimental clip embed enhancement through tiling
...
Allows more detail in the clip embeds as well as details from non square images without stretching
Idea and most of the code is from Matteo:
https://github.com/cubiq/ComfyUI_IPAdapter_plus/blob/9d076a3df0d2763cef5510ec5ab807f6632c39f5/utils.py#L181
2025-03-21 19:41:49 +02:00
kijai
173aff2367
fix I2V flowedit and maybe allow compile with vram management
2025-03-16 03:00:14 +02:00
kijai
81a08d0e59
Make non_blocking offloading optional for low RAM usecases
2025-03-16 01:48:45 +02:00
kijai
d455cc89a3
vram management fix
2025-03-15 16:40:39 +02:00
kijai
58e5737032
Add option to use comfy native RoPE calculations
...
comfy rope doesn't use complex numbers and can be torch.compiled, then it's faster and uses less memory
2025-03-15 15:45:53 +02:00
kijai
ff4bb8085e
remove print
2025-03-13 18:17:46 +02:00
kijai
8ac0da07c6
Add SLG
...
Credits to AmericanPresidentJimmyCarter: https://github.com/deepbeepmeep/Wan2GP/pull/61
2025-03-13 17:29:15 +02:00
kijai
f07850cf9c
fix vram management
2025-03-13 02:41:55 +02:00
kijai
71fd6c7208
rope tweaks
2025-03-13 02:26:40 +02:00
kijai
cd9e9dc891
Update model.py
2025-03-12 19:58:53 +02:00
kijai
5c63ff5bce
Faster RoPE
2025-03-12 18:36:28 +02:00
kijai and spacepxl
ffaf1afe4e
Support control-lora
...
https: //huggingface.co/spacepxl/Wan2.1-control-loras/blob/main/wan2.1-1.3b-control-lora-tile-v0.1_comfy.safetensors
Co-Authored-By: spacepxl <143970342+spacepxl@users.noreply.github.com >
2025-03-10 21:31:06 +02:00
kijai
07848ab0b5
fix
2025-03-09 23:26:46 +02:00
kijai
5a68948607
enhance-a-video tweak
2025-03-09 18:42:06 +02:00
kijai
389bbd343c
Update TeaCache docs
2025-03-08 12:13:52 +02:00
kijai
32465c2787
TeaCache tweaks for context windowing and FlowEdit
2025-03-05 21:02:34 +02:00
kijai
de3e0f9ef2
update TeaCache
2025-03-05 13:35:18 +02:00
kijai
c4472c2906
Add FlowEdit and some code refactors
2025-03-05 00:54:08 +02:00
kijai
013fae65fb
cleanup
2025-03-04 01:56:13 +02:00
kijai
0183a03bf9
revert and fix again...
...
I'll clean this later
2025-03-03 01:38:51 +02:00
kijai
24fb1b42fe
bug fixes
2025-03-03 01:35:36 +02:00
kijai
d3129c6996
Add alternative offloading method from Diffsynth
2025-03-02 14:37:08 +02:00
kijai
ac98a0318b
Update model.py
2025-03-02 10:52:25 +02:00
kijai
55dcc33d00
Add block swap debug prints and cleanup unused code
2025-03-02 10:49:46 +02:00
kijai
9087791b75
Allow setting TeaCache device to avoid the VRAM usage increase
2025-03-02 09:57:02 +02:00
zhuhz22
b366a40ab6
fix: riflex
2025-03-02 14:38:08 +08:00
kijai
fa3d61cb45
Cleanup the text part of the clip model as redundant as it's not even used
2025-03-02 01:44:19 +02:00
kijai
fbb432ce0f
Experimental TeaCache
...
I haven't figured out the whole coefficiency calculation part, however I noticed it's already super close to the time embed as it is, if we just skip the initial steps from the calculations. Seems to work okayish with the 1.3B model at least.
2025-03-02 01:34:55 +02:00
kijai
df6d0b677f
Make I2V resolution adjustment optional and other tweaks
2025-03-01 16:58:10 +02:00
kijai
25fd487f86
better error handling for sageattn loading
2025-03-01 03:05:38 +02:00
kijai
889efe7371
fix
2025-02-28 18:00:31 +02:00
kijai
7a6418a953
Fix something stupid and start implementing context schedule
2025-02-28 15:56:19 +02:00
kijai
076ba55b1d
Use fp16_accumulation if available when using fp16 base_precision
2025-02-28 12:22:41 +02:00
kijai
dd3eedcd86
Add enhance-a-video, start Spargeattn testing
2025-02-28 00:49:17 +02:00
kijai
9e957121be
better preview
2025-02-27 11:13:30 +02:00
kijai
3c70da4192
Update attention.py
2025-02-26 12:17:52 +02:00
kijai
0a020a6f18
maybe fix flash attention
2025-02-26 12:15:35 +02:00
kijai
7606f28122
less spammy blockswap
2025-02-26 12:12:48 +02:00
kijai
7e19d75480
fp8 option for T5
2025-02-26 11:35:52 +02:00
kijai
b3a816698a
torch compile fixes
2025-02-26 11:10:27 +02:00
kijai
fd730326c9
support LoRAs
2025-02-26 08:43:28 +02:00
kijai
f5add63007
don't need the text encoder
2025-02-26 02:53:41 +02:00
kijai
2d1afe1c3d
fixes
2025-02-26 02:42:03 +02:00
kijai
518013fd18
cleanup
2025-02-25 22:13:48 +02:00
kijai