 kijai
|
e3a2fa7ca7
|
remove noise from preview
|
2025-01-06 12:45:17 +02:00 |
|
|
kijai
|
2eb34af146
|
Fix previews for rf-inversion too
|
2025-01-06 11:45:01 +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
|
783d111459
|
fix
|
2025-01-06 06:46:53 +02:00 |
|
|
kijai
|
6c70beda52
|
Add TeaCache
|
2025-01-06 06:26:28 +02:00 |
|
|
kijai
|
46e31f1a44
|
Update nodes_rf_inversion.py
|
2024-12-23 18:03:36 +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
|
2fe649be41
|
compile fixes
|
2024-12-23 11:42:20 +02:00 |
|
|
kijai
|
1614fb2f3c
|
feta for rf inversion
|
2024-12-22 02:23:32 +02:00 |
|
|
kijai
|
6a10cf7101
|
Update nodes_rf_inversion.py
|
2024-12-22 02:15:15 +02:00 |
|
|
kijai
|
c9d1d415c1
|
Merge branch 'main' of https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
|
2024-12-22 02:04:10 +02:00 |
|
|
kijai
|
cbfc632933
|
Prevent unloading LoRAs if multiple model loaders are used
|
2024-12-22 02:04:07 +02:00 |
|
|
Jukka Seppänen
|
4028950538
|
Update readme.md
|
2024-12-21 19:23:40 +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
|
da2fb54468
|
remove print
|
2024-12-19 17:03:10 +02:00 |
|
|
kijai
|
efec814c37
|
better preview
from upstream comfyui
|
2024-12-19 14:12:42 +02:00 |
|
|
Jukka Seppänen
|
e71cf2b931
|
Update readme.md
|
2024-12-19 14:02:02 +02:00 |
|
|
Jukka Seppänen
|
513b3adcbc
|
Update readme.md
|
2024-12-19 14:01:34 +02:00 |
|
|
Jukka Seppänen
|
9798e3f4ec
|
Update readme.md
|
2024-12-19 14:01:13 +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 |
|
|
Jukka Seppänen
|
8a273842c6
|
Update readme.md
|
2024-12-17 14:06:18 +02:00 |
|
|
kijai
|
879b039b0e
|
update examples
|
2024-12-16 21:26:37 +02:00 |
|
|
kijai
|
6a138f063b
|
Merge branch 'pr/149'
|
2024-12-16 21:16:41 +02:00 |
|
|
kijai
|
aad20fa749
|
update example
|
2024-12-16 21:15:26 +02:00 |
|
|
kijai
|
8f7710a77c
|
Avoid trying to create preprocessor with encoder only model
|
2024-12-16 21:12:02 +02:00 |
|
|
Jukka Seppänen
|
86e6faf175
|
Add experimental prompt mix sampler, add optional interpolation curves for rf-inversion
pseudo prompt travel thing, sometimes works, very experimental
|
2024-12-15 23:26:16 +02:00 |
|
|
Dango233
|
f169e83438
|
UPDATE readme.md
|
2024-12-15 22:59:00 +08:00 |
|
|
Dango233
|
7b2687d3f4
|
Merge pull request #2 from Dango233/dango233/ip2v-for-merging
* TextImage Encoder now a seperate node.
|
2024-12-15 22:17:03 +08:00 |
|
|
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
|
4e639f3ad7
|
Update readme.md
|
2024-12-15 18:49:43 +08:00 |
|
|
Dango233
|
9c8598ec2b
|
Update readme.md
|
2024-12-15 17:15:26 +08:00 |
|
|
Dango233
|
c9bd1c1a28
|
Update readme.md
|
2024-12-15 17:07:48 +08:00 |
|
|
Dango233
|
bb75fb63d5
|
Update readme.md
|
2024-12-15 17:07:09 +08:00 |
|
|
Dango233
|
d5891eb050
|
Merge pull request #1 from Dango233/dango233/ip2v
IP2V - Experimental implementation based on Kijai Nodes, Initial Commit
|
2024-12-15 17:05:08 +08:00 |
|
|
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
|
2ce2f48c24
|
Update requirements.txt
|
2024-12-14 11:52:05 +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 |
|
|
Jukka Seppänen
|
eba2273d16
|
Merge pull request #133 from tdrussell/lora
Support Diffusers LoRA format
|
2024-12-13 08:46:33 +02:00 |
|