kijai
|
fdb23dec7d
|
Update model.py
|
2026-01-05 22:11:04 +02:00 |
|
kijai
|
07d7d8ca8e
|
remove prints
|
2026-01-05 22:10:02 +02:00 |
|
kijai
|
01869d4bf5
|
Merge branch 'main' into longvie2
|
2026-01-05 18:47:48 +02:00 |
|
kijai
|
bf1d77fe15
|
Update wan_video_vae.py
|
2025-12-31 15:56:10 +02:00 |
|
kijai
|
cced7fefbe
|
Make VAE memory reporting optional to reduce log spam, and other logging updates
|
2025-12-31 15:46:40 +02:00 |
|
kijai
|
36bb0c73ee
|
Correct infinite talk loop log entry
Just visual bug, no effect on anything else
|
2025-12-31 14:50:27 +02:00 |
|
kijai
|
b982b4ef0c
|
Update nodes_model_loading.py
|
2025-12-30 02:55:51 +02:00 |
|
kijai
|
3a7100bc39
|
Add node for UltraVico params
|
2025-12-30 02:53:38 +02:00 |
|
kijai
|
55c672028b
|
Merge branch 'main' into longvie2
|
2025-12-29 15:39:43 +02:00 |
|
kijai
|
be41f67fae
|
Fix res_multistep steps
|
2025-12-29 15:39:27 +02:00 |
|
kijai
|
351829a2b6
|
Fix er_sde steps
|
2025-12-29 15:36:43 +02:00 |
|
kijai
|
b551ec9e31
|
Merge branch 'main' into longvie2
|
2025-12-29 15:03:53 +02:00 |
|
kijai
|
19bcee67ed
|
remove print
|
2025-12-29 02:50:04 +02:00 |
|
kijai
|
2fe4834178
|
Adjust ultravico frame_tokens
|
2025-12-29 02:48:59 +02:00 |
|
kijai
|
486564060f
|
Add node to set attention mode per step and/or blocks
|
2025-12-29 01:35:32 +02:00 |
|
kijai
|
3730ccf603
|
Fix s2v
|
2025-12-28 10:34:13 +02:00 |
|
kijai
|
1eab022bb0
|
Update nodes.py
|
2025-12-28 02:35:42 +02:00 |
|
kijai
|
6fd4c6640c
|
Adjust scheduler graph drawing
|
2025-12-28 01:27:18 +02:00 |
|
kijai
|
7a6efc1456
|
Add node for SVI 2.0 Pro
|
2025-12-28 00:35:14 +02:00 |
|
kijai
|
e855726f10
|
Fix enhance-a-video
|
2025-12-26 23:12:18 +02:00 |
|
kijai
|
a896101ec8
|
I don't know why this suddenly errors
|
2025-12-26 22:28:04 +02:00 |
|
kijai
|
fd818faa08
|
Fix context window ref latent device
|
2025-12-26 16:09:01 +02:00 |
|
kijai
|
b132a82f7a
|
Fix LongCat-Avatar audio padding when not enough audio provided for given window
|
2025-12-26 15:57:30 +02:00 |
|
kijai
|
4b709a7a04
|
Cleanup example_workflows folder some
|
2025-12-26 15:44:08 +02:00 |
|
kijai
|
220aac2771
|
Update LongCatAvatar_audio_image_to_video_example_01.json
|
2025-12-26 13:52:27 +02:00 |
|
kijai
|
027bed8c3d
|
Cleanup
|
2025-12-26 13:51:05 +02:00 |
|
kijai
|
b2c520ca44
|
Fix s2v
|
2025-12-26 12:55:13 +02:00 |
|
kijai
|
20942b8fd9
|
Cleanup: Remove flowedit code, restructure some other code
Due to lack of use and code maintainability
|
2025-12-26 12:51:22 +02:00 |
|
kijai
|
74f337e06c
|
Adjust StoryMem lora scaling
This was probably too high afterall
|
2025-12-26 01:41:32 +02:00 |
|
kijai
|
264212dddb
|
Fix uncond variable name when using zero star or fresca
|
2025-12-26 01:27:48 +02:00 |
|
kijai
|
f988d19fdb
|
StoryMem latents are supposed to be encoded one by one
|
2025-12-25 20:44:37 +02:00 |
|
kijai
|
95255c7ffa
|
Add node to add story memory latents
|
2025-12-24 18:44:05 +02:00 |
|
kijai
|
c42bf94b07
|
Automatically adjust LoRA alpha for Peft rs_lora weights
At least the original StoryMem -LoRAs need this
|
2025-12-24 17:58:30 +02:00 |
|
kijai
|
dcae850b96
|
Allow higher lora scale
|
2025-12-24 17:07:59 +02:00 |
|
kijai
|
9f019d7dfb
|
Merge branch 'main' into longvie2
|
2025-12-23 23:40:25 +02:00 |
|
kijai
|
c5d3fb450c
|
Allow loading StoryMem -LoRAs
https://huggingface.co/Kevin-thu/StoryMem
|
2025-12-23 22:26:37 +02:00 |
|
kijai
|
f28e7da442
|
version 1.4.5
|
2025-12-23 22:16:03 +02:00 |
|
kijai
|
ac7d8cab98
|
Update LongCatAvatar_audio_image_to_video_example_01.json
|
2025-12-23 22:05:02 +02:00 |
|
kijai
|
fc5322fae4
|
Merge branch 'main' into longvie2
|
2025-12-23 22:04:15 +02:00 |
|
kijai
|
e75f814312
|
LongCat-Avatar example
|
2025-12-23 20:43:10 +02:00 |
|
kijai
|
222fc70eb7
|
Update nodes.py
|
2025-12-23 17:18:55 +02:00 |
|
kijai
|
8509236da1
|
init
|
2025-12-23 14:20:18 +02:00 |
|
kijai
|
1c24ef50f8
|
Remove print
|
2025-12-23 12:25:55 +02:00 |
|
kijai
|
5360eeb345
|
Squashed commit of the following:
commit fd32b14fdc
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Tue Dec 23 02:02:31 2025 +0200
Clean prints
commit 1776695e26
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Tue Dec 23 01:48:12 2025 +0200
Update nodes_model_loading.py
commit ef36204fa8
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Tue Dec 23 01:35:08 2025 +0200
Reduce peak VRAM use
commit c6f32c1424
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Mon Dec 22 23:53:41 2025 +0200
Norm dtype
commit 6d4a0f6e53
Merge: e7e0006 3e45021
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Mon Dec 22 22:11:38 2025 +0200
Merge branch 'main' into longcat_avatar
commit e7e00061e5
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Mon Dec 22 00:43:01 2025 +0200
Update nodes_sampler.py
commit eb5ec262a0
Merge: 7c0ba84 fed3b22
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Mon Dec 22 00:42:53 2025 +0200
Merge branch 'main' into longcat_avatar
commit 7c0ba84a26
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Sun Dec 21 23:00:43 2025 +0200
remove prints
commit 06a86923e7
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Sun Dec 21 22:53:25 2025 +0200
Fix ref latent
oops
commit dca3106f10
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Sat Dec 20 18:46:32 2025 +0200
Expose more options, make vid2vid easier
commit 175418b8d2
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Sat Dec 20 03:15:24 2025 +0200
Create LongCatAvatar_testing_wip.json
commit 4a6e2d3c6c
Author: kijai <40791699+kijai@users.noreply.github.com>
Date: Sat Dec 20 03:14:49 2025 +0200
Init
|
2025-12-23 12:17:07 +02:00 |
|
kijai
|
3e45021422
|
Support mixed precision fp8 scaled models
|
2025-12-22 21:40:14 +02:00 |
|
kijai
|
41683a0423
|
Possibly fix uni3c + multitalk
|
2025-12-22 19:44:53 +02:00 |
|
kijai
|
0ac7401271
|
Stand-in RoPE adjustments
The offset was a bit wrong
|
2025-12-22 18:56:04 +02:00 |
|
kijai
|
fed3b22bc9
|
Update nodes_sampler.py
|
2025-12-21 15:06:46 +02:00 |
|
kijai
|
392d0305fc
|
Add portrait_cfg
|
2025-12-21 15:06:14 +02:00 |
|
kijai
|
be411bdef6
|
Support loading FlashPortrait model
Can just re-use FantasyPortrait for basic usage
|
2025-12-20 19:56:26 +02:00 |
|