kijai
2cfae9fa8f
Make UniAnimate ref pose optional
2025-04-19 17:41:04 +03:00
kijai
90c9415d31
Add lcm scheduler, pad/truncate UniAnim poses if pose count doesn't match latent count
2025-04-19 17:24:18 +03:00
kijai
421e375f13
Strength controls for Unianimate
2025-04-18 23:06:49 +03:00
kijai
7462356743
Support UniAnimate-DiT
...
https://github.com/ali-vilab/UniAnimate-DiT
2025-04-18 19:43:40 +03:00
kijai
8257cd1f8a
Fix TeaCache end step
2025-04-17 01:18:42 +03:00
kijai
7c81d7ce10
Better support for the official FirstLastFrame2Video -model (FLF2V)
...
https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1-FLF2V-14B-720P_fp16.safetensors
https://huggingface.co/Kijai/WanVideo_comfy/blob/main/Wan2_1-FLF2V-14B-720P_fp8_e4m3fn.safetensors
2025-04-16 19:40:04 +03:00
kijai
f919c4fd3d
Allow using custom sigmas, fix some cases with multiple VACE embeds
2025-04-13 16:35:40 +03:00
kijai
941acc434d
Add some schedulers
2025-04-12 17:18:53 +03:00
kijai
2dc25c150e
allow other dimensions
2025-04-11 00:56:54 +03:00
kijai
94f59f09c8
map camera types
2025-04-10 23:27:36 +03:00
kijai
740fdd749a
initial recammaster support
2025-04-10 23:04:32 +03:00
kijai
280f9952e5
Fix fp32 with some versions of sageattn
2025-04-10 12:10:44 +03:00
kijai
8570c7dbe8
Temporary fix for vram_management
2025-04-09 10:04:29 +03:00
kijai
179f85bf3d
less unnecessary recompiles
2025-04-09 01:11:30 +03:00
kijai
f3f12aa6cf
Fix batched_cfg and some possible dtype tweaks to avoid recompiles
2025-04-08 20:08:33 +03:00
kijai
7de8ac25a6
Some VACE tweaks
2025-04-08 18:27:06 +03:00
kijai
7d23826136
tiled encoding fixes and add as option for VACE endore
2025-04-07 20:21:36 +03:00
kijai
dce705f5d7
Further reduce VRAM use of VACE when block swapping enabled
2025-04-06 21:55:52 +03:00
kijai
a05d3ac8ac
Considerably reduce VACE memory use
...
I don't understand why the initial code did it like it did, keeping the VACE results as a list uses way less memory and so far haven't faced any issues and results remain identical.
2025-04-06 17:18:13 +03:00
kijai
1d91e497aa
bit better VACE offloading
2025-04-06 12:13:36 +03:00
kijai
04534e5eed
Allow using multiple VACE embeds, fix VACE blockswap error when vace blocks not set and blockswap is set
...
Experimental
2025-04-04 15:23:39 +03:00
kijai
e4912d03de
non_blocking teacache offload
2025-04-03 20:06:15 +03:00
kijai
1aa6498bbe
Compile VACE blocks as well
2025-04-03 17:05:39 +03:00
kijai
4cebb55032
more robust vace check
2025-04-02 18:41:39 +03:00
kijai
390bc2a6cb
Update model.py
2025-04-02 18:38:16 +03:00
kijai
c33ba8b05c
Update model.py
2025-04-02 18:27:40 +03:00
kijai
f820f38c8f
Allow offloading and block swapping VACE blocks as well
2025-04-02 17:27:17 +03:00
kijai
0801394cb5
Fix TeaCache memory issue
2025-04-02 16:14:24 +03:00
kijai
ce6522c227
Add start/end percent controls for VACE
2025-04-02 11:10:12 +03:00
kijai
96b236c4df
Basic VACE (preview version) support
...
no ref image or masking yet, but control signal seems to work
2025-04-01 22:05:33 +03:00
kijai
3869b0482b
cleanup
2025-04-01 19:13:53 +03:00
kijai
23c9a6d634
Add dynamo_recompile_limit as adjustable option, revert to old euler for flowedit
2025-04-01 11:44:45 +03:00
kijai
91f0ccc594
revert this
2025-03-31 01:51:49 +03:00
kijai
facf65aec6
Allow using more than one start_image with the Fun InP models
2025-03-30 23:06:28 +03:00
kijai
4970f84f5f
Update wan_video_vae.py
2025-03-30 16:17:17 +03:00
kijai
104c632359
some cleanup
2025-03-28 01:58:47 +02:00
kijai
2d56d69ccb
Add alternative TeaCache mode, better frame matching for control workflow
...
Based on the coefficients from here:
https://github.com/ali-vilab/TeaCache/pull/51
2025-03-27 19:44:37 +02:00
kijai
921e577ad9
Update model.py
2025-03-26 18:59:13 +02:00
kijai
e5df47a2d3
Support Fun-InP control T2V
2025-03-26 18:36:08 +02:00
kijai
0e0962d6e8
support 1.3B Fun Control -model
2025-03-26 16:39:27 +02:00
kijai
a1938107cd
Allow splitting self attention as well when using multiple prompts
2025-03-25 21:05:08 +02:00
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 and raindrop313
f8f423ecee
Experimental end frame feature, refactor image to vid encoding
...
VAE modification code from:
https: //github.com/raindrop313/ComfyUI-WanVideoStartEndFrames/
Co-Authored-By: raindrop313 <87897973+raindrop313@users.noreply.github.com >
2025-03-20 16:48:04 +02:00
kijai
173aff2367
fix I2V flowedit and maybe allow compile with vram management
2025-03-16 03:00:14 +02:00
kijai