 kijai
|
d74561122c
|
Load textencoder to RAM by default
|
2025-02-02 16:49:26 +02:00 |
|
|
kijai
|
e34492ad47
|
noise augment for i2v
|
2025-02-01 15:13:40 +02:00 |
|
|
kijai
|
1c966f0ee7
|
workaround for unload_all_models removing LoRA
|
2025-01-25 20:21:59 +02:00 |
|
|
kijai
|
863e15fe92
|
Update nodes.py
|
2025-01-25 14:09:44 +02:00 |
|
|
kijai
|
0ff6646f94
|
Update nodes.py
|
2025-01-24 17:14:56 +02:00 |
|
|
kijai
|
5d7b0e4339
|
Support leapfusion img2vid
https://github.com/AeroScripts/leapfusion-hunyuan-image2video
|
2025-01-24 17:11:16 +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
|
a66045fef4
|
tiny category fix
|
2025-01-14 14:38:39 +02:00 |
|
|
kijai
|
836b26aff3
|
scheduler fixes
|
2025-01-10 00:36:58 +02:00 |
|
|
kijai
|
11ee15a91e
|
Support VHS animated previews
|
2025-01-07 00:39:09 +02:00 |
|
|
kijai
|
4fe87a3220
|
Some more schedulers
|
2025-01-06 19:17:46 +02:00 |
|
|
kijai
|
e8e0ac4e56
|
support using comfy native VAE decoding
|
2025-01-06 14:58:05 +02:00 |
|
|
kijai
|
1d67d090da
|
Fix preview
|
2025-01-06 11:38:40 +02:00 |
|
|
kijai
|
03801b426f
|
Add dpm++ scheduler
|
2025-01-06 02:27:29 +02:00 |
|
|
kijai
|
6c70beda52
|
Add TeaCache
|
2025-01-06 06:26:28 +02:00 |
|
|
kijai
|
ebb267bc74
|
Update nodes.py
|
2024-12-23 17:57:21 +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
|
1614fb2f3c
|
feta for rf inversion
|
2024-12-22 02:23:32 +02:00 |
|
|
kijai
|
cbfc632933
|
Prevent unloading LoRAs if multiple model loaders are used
|
2024-12-22 02:04:07 +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
|
26aaa26a4a
|
Update nodes.py
|
2024-12-21 01:35:41 +02:00 |
|
|
kijai
|
b6c1705f9f
|
simple context windows with freenoise shuffling
|
2024-12-19 11:56:53 +02:00 |
|
|
kijai
|
ec0fdf1fc4
|
consistently use safe_load
|
2024-12-19 01:53:00 +02:00 |
|
|
kijai
|
fb34e91f0e
|
Support official scaled fp8 model
|
2024-12-18 10:29:56 +02:00 |
|
|
kijai
|
46f569f571
|
clearer error on frame count mismatch
|
2024-12-18 00:34:12 +02:00 |
|
|
Dango233
|
fbfaa8d900
|
* TextImage Encoder now a seperate node.
* No more behavior change of original nodes
* Clean up
|
2024-12-15 14:14:28 +00:00 |
|
|
Dango233
|
a3fbc3df80
|
IP2V - Experimental implementation based on Kijai Nodes, Initial Commit
|
2024-12-15 09:02:33 +00:00 |
|
|
kijai
|
ecae5f270e
|
small fixes
|
2024-12-14 22:28:02 +02:00 |
|
|
kijai
|
4c5507ffc6
|
Add fp8 as quant choice for the LLM, fix using custom clip_l with cfg
|
2024-12-14 16:36:25 +02:00 |
|
|
kijai
|
8a6e36a548
|
Update nodes.py
|
2024-12-14 00:48:54 +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
|
764dad6975
|
make offload_device work again
|
2024-12-13 12:25:54 +02:00 |
|
|
kijai
|
a46c3491a0
|
Update nodes.py
|
2024-12-13 11:10:59 +02:00 |
|
|
tdrussell
|
c1303fa205
|
Support Diffusers LoRA format
|
2024-12-12 21:12:13 -06:00 |
|
|
kijai
|
1307c1fe31
|
rf inversion fixes
|
2024-12-13 01:04:33 +02:00 |
|
|
kijai
|
5f5b71dc62
|
Move LoRA loading to model loader
|
2024-12-12 21:00:51 +02:00 |
|
|
tdrussell
|
225518bc64
|
Merge remote-tracking branch 'origin/main' into lora
|
2024-12-11 10:32:11 -06:00 |
|
|
kijai
|
6ab3d0ae62
|
initial RF-inversion for testing
|
2024-12-11 16:27:10 +02:00 |
|
|
kijai
|
2d00a9ad7c
|
fix vae node defaults
|
2024-12-11 10:56:12 +02:00 |
|
|
tdrussell
|
de1a04e879
|
Merge remote-tracking branch 'origin/main' into lora
|
2024-12-10 00:36:28 -06:00 |
|
|
kijai
|
e7212f184f
|
VAE encode fixes
|
2024-12-09 21:03:16 +02:00 |
|
|
kijai
|
0968d87a9d
|
Update nodes.py
|
2024-12-09 20:41:55 +02:00 |
|
|
kijai
|
a01b0796be
|
VAE fixes and more options
|
2024-12-09 19:20:45 +02:00 |
|
|
tdrussell
|
9cc751a13f
|
LoRA support
|
2024-12-08 17:41:42 -06:00 |
|
|
kijai
|
9a4abbc535
|
Allow using comfy clip_l, fix fp8 fastmode mem use
|
2024-12-08 20:34:31 +02:00 |
|
|
kijai
|
11530dcb8e
|
Update nodes.py
|
2024-12-08 18:02:13 +02:00 |
|
|
kijai
|
ec00443395
|
Allow using custom prompt_templates
|
2024-12-08 17:08:06 +02:00 |
|
|
kijai
|
62d22a7ba9
|
support single image gen
|
2024-12-08 12:27:18 +02:00 |
|
|
kijai
|
e9e058436e
|
block_swap tweaks
|
2024-12-08 01:44:16 +02:00 |
|