 kijai
|
675baf7574
|
fix
|
2025-05-09 16:56:29 +03:00 |
|
|
kijai
|
9a5d192807
|
more TeaCache fixes..
|
2025-05-09 16:43:35 +03:00 |
|
|
kijai
|
14cc8ae0a5
|
TeaCache fixes
|
2025-05-09 16:36:00 +03:00 |
|
|
kijai
|
27e541b0a5
|
Update models.py
|
2025-05-09 15:05:40 +03:00 |
|
|
kijai
|
91aabfc857
|
fixes
|
2025-05-09 14:59:44 +03:00 |
|
|
kijai
|
6682a0905e
|
Add SLG
For testing, no clue what blocks to use at this point
|
2025-05-09 14:10:55 +03:00 |
|
|
kijai
|
e18afda414
|
Add TeaCache start/end step
|
2025-05-09 11:41:31 +03:00 |
|
|
kijai
|
6ea4d31b41
|
initial hunyuan custom support
|
2025-05-09 09:16:02 +03:00 |
|
|
kijai
|
7f92dcb5f2
|
Allow using comfy text encoding, stop using text_mask to fix normal sageattn and improve sdpa
|
2025-03-09 23:33:26 +02:00 |
|
|
kijai
|
0f2c41040d
|
Add keyframe example
|
2025-03-08 21:51:18 +02:00 |
|
|
kijai
|
e9b0b79132
|
reset teacache stats
|
2025-03-08 11:01:14 +02:00 |
|
|
kijai
|
02b875b717
|
Add device option for teacache
|
2025-03-08 01:20:20 +02:00 |
|
|
kijai
|
d4d93377e5
|
fix stability mode for the old model, add vae dist mode selection
|
2025-03-07 22:38:04 +02:00 |
|
|
kijai
|
ab1fcc6b31
|
Initial support for the fixed model (might break other things for now)
|
2025-03-07 21:41:38 +02:00 |
|
|
kijai
|
bcfef4de33
|
Support official I2V
|
2025-03-06 10:34:51 +02:00 |
|
|
kijai
|
e13d384ef7
|
small fixes
|
2025-02-18 11:01:04 +02:00 |
|
|
kijai
|
63717f733a
|
cleanup
|
2025-02-18 04:30:05 +02:00 |
|
|
kijai
|
ea1b92cfc2
|
RoPE optimizations and fix
- small overall speed boost and fix freqs dtype
- allow not upcasting RoPE for slight speed boost
|
2025-01-17 16:57:37 +02:00 |
|
|
kijai
|
6c70beda52
|
Add TeaCache
|
2025-01-06 06:26:28 +02:00 |
|
|
kijai
|
f52a49f1d8
|
Add alternative cpu offloading
Thanks to the DiffSynth team:
https://github.com/modelscope/DiffSynth-Studio/blob/main/diffsynth/models/hunyuan_video_dit.py#L630
|
2024-12-23 17:47:09 +02:00 |
|
|
kijai
|
b9ea9bf7cd
|
Add Enhance-A-Video
https://github.com/NUS-HPC-AI-Lab/Enhance-A-Video/
|
2024-12-21 17:42:07 +02:00 |
|
|
kijai
|
46f569f571
|
clearer error on frame count mismatch
|
2024-12-18 00:34:12 +02:00 |
|
|
kijai
|
ecae5f270e
|
small fixes
|
2024-12-14 22:28:02 +02:00 |
|
|
kijai
|
4a81c5ec94
|
Add CFG as optional node
experimental, using CFG halves the inference speed but allows using negative prompt, possibly more useful when using LoRAs
|
2024-12-13 16:59:49 +02:00 |
|
|
kijai
|
706c3a07ef
|
Add nodes for text embed saving/loading
This way you can encode prompts in separate workflow to avoid ever having to load the text encoders for sampling if you're low on RAM
|
2024-12-13 13:07:34 +02:00 |
|
|
kijai
|
9a4abbc535
|
Allow using comfy clip_l, fix fp8 fastmode mem use
|
2024-12-08 20:34:31 +02:00 |
|
|
kijai
|
d49a711cd8
|
Update models.py
|
2024-12-08 02:00:41 +02:00 |
|
|
kijai
|
f5d80350c0
|
remove prints
|
2024-12-08 01:47:06 +02:00 |
|
|
kijai
|
e9e058436e
|
block_swap tweaks
|
2024-12-08 01:44:16 +02:00 |
|
|
kijai
|
929781949e
|
Add STG start/end percent
|
2024-12-07 21:51:37 +02:00 |
|
|
kijai
|
0cbcc20a89
|
initial STG testing
|
2024-12-06 17:09:56 +02:00 |
|
|
kijai
|
2e8f1f2fbd
|
fix flash_attn, make sdpa default
|
2024-12-06 11:12:10 +02:00 |
|
|
kijai
|
31950d0b55
|
possibly fix up sdpa
|
2024-12-06 03:15:02 +02:00 |
|
|
kijai
|
3197107b5e
|
fixup block_swap start
|
2024-12-04 03:53:51 +02:00 |
|
|
kijai
|
1073ef9156
|
custom block_swap to reduce VRAM use
thanks to 2kpr for the initial block swap code!
|
2024-12-04 02:13:48 +02:00 |
|
|
kijai
|
fa45b717fe
|
Update models.py
|
2024-12-03 19:14:00 +02:00 |
|
|
kijai
|
73b49a30a6
|
initial commit
|
2024-12-03 19:09:50 +02:00 |
|