 kijai
|
e258b0fa57
|
Support dashtoon keyframe-control LoRA
https://github.com/dashtoon/hunyuan-video-keyframe-control-lora
Converted:
https://huggingface.co/Kijai/HunyuanVideo_comfy/blob/main/HunyuanVideo_dashtoon_keyframe_lora_converted_bf16.safetensors
|
2025-03-08 20:56:48 +02:00 |
|
|
kijai
|
4bc21fdece
|
Probably irrelevant, cleanup
|
2025-03-08 12:11:04 +02:00 |
|
|
kijai
|
2559003f40
|
Add option to skip latents on decode node
Helps to mitigate the flashing on the new I2V results
|
2025-03-08 11:21:54 +02:00 |
|
|
kijai
|
e9b0b79132
|
reset teacache stats
|
2025-03-08 11:01:14 +02:00 |
|
|
kijai
|
5f88a38edd
|
bump version
|
2025-03-08 10:12:08 +02:00 |
|
|
kijai
|
a20d994030
|
Fix leapfusion and V2V
|
2025-03-08 09:58:47 +02:00 |
|
|
kijai
|
3c230c723b
|
Update nodes.py
|
2025-03-08 01:28:29 +02:00 |
|
|
kijai
|
02b875b717
|
Add device option for teacache
|
2025-03-08 01:20:20 +02:00 |
|
|
kijai
|
e332935ad6
|
Fix skyreels
|
2025-03-08 00:17:01 +02:00 |
|
|
kijai
|
173a85d356
|
Remove the normal sageattn -mode as it doesn't work properly.
|
2025-03-08 00:11:15 +02:00 |
|
|
kijai
|
18324a91da
|
Update hyvideo_i2v_example_fixed_model_02.json
|
2025-03-08 00:04:27 +02:00 |
|
|
kijai
|
f4917860e9
|
Update pipeline_hunyuan_video.py
|
2025-03-07 23:57:56 +02:00 |
|
|
kijai
|
21db5cf039
|
fix T2V
|
2025-03-07 23:52:15 +02:00 |
|
|
kijai
|
00dc5dfa2a
|
Update pyproject.toml
|
2025-03-07 23:45:29 +02:00 |
|
|
kijai
|
333b91a237
|
update reqs
|
2025-03-07 23:23:52 +02:00 |
|
|
kijai
|
a691a63e93
|
Create hyvideo_i2v_example_fixed_model_02.json
|
2025-03-07 22:57:13 +02:00 |
|
|
kijai
|
0935213be2
|
fixed model fixes
|
2025-03-07 22:54:18 +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
|
bf94665f8b
|
Don't break skyreels
|
2025-03-07 21:50:44 +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
|
5291557fd6
|
Update pyproject.toml
|
2025-03-07 01:21:40 +02:00 |
|
|
kijai
|
a2c99e6864
|
fix IP2V -node
|
2025-03-06 23:50:21 +02:00 |
|
|
kijai
|
e4b52667d6
|
Update pipeline_hunyuan_video.py
|
2025-03-06 23:09:37 +02:00 |
|
|
kijai
|
16b2c11d2b
|
Pad the input by one latent when using I2V
Seems better as we drop the first latent at end anyway
|
2025-03-06 20:09:51 +02:00 |
|
|
kijai
|
d8bd580842
|
This was still in latent space...
duh
|
2025-03-06 18:46:18 +02:00 |
|
|
kijai
|
4863a2af8d
|
Update nodes.py
|
2025-03-06 13:14:33 +02:00 |
|
|
kijai
|
9fc32187e6
|
Update nodes.py
|
2025-03-06 13:13:47 +02:00 |
|
|
kijai
|
aafb014e48
|
use original bucket sizes
|
2025-03-06 11:54:58 +02:00 |
|
|
kijai
|
5c150503fa
|
Update pyproject.toml
|
2025-03-06 11:14:37 +02:00 |
|
|
kijai
|
f80559d7c6
|
Update hyvideo_i2v_example_01.json
|
2025-03-06 11:03:52 +02:00 |
|
|
kijai
|
5fe58f314b
|
Create hyvideo_i2v_example_01.json
|
2025-03-06 10:56:25 +02:00 |
|
|
kijai
|
22d5225e35
|
Merge branch 'main' of https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
|
2025-03-06 10:35:34 +02:00 |
|
|
kijai
|
bcfef4de33
|
Support official I2V
|
2025-03-06 10:34:51 +02:00 |
|
|
Jukka Seppänen
|
2b043839ae
|
Merge pull request #411 from zhuhz22/riflex
fix: implementation of riflex (only apply riflex on the temporal axis)
|
2025-03-01 17:39:35 +02:00 |
|
|
kijai
|
848168b8e4
|
Add RifleX, ability to generate more frames without looping
https://github.com/thu-ml/RIFLEx
|
2025-02-24 23:05:09 +02:00 |
|
|
kijai
|
28ba2dc638
|
Better error for incompatible VAE
|
2025-02-23 14:25:36 +02:00 |
|
|
kijai
|
5cbc584b68
|
add timm to reqs
|
2025-02-22 13:47:07 +02:00 |
|
|
kijai
|
8e0283bb3c
|
bump version
|
2025-02-21 19:24:09 +02:00 |
|
|
kijai
|
ecd60a66e6
|
Update nodes.py
|
2025-02-18 22:25:30 +02:00 |
|
|
kijai
|
33950e9168
|
update skyreel I2V example
|
2025-02-18 21:50:09 +02:00 |
|
|
kijai
|
375334a727
|
bump version
|
2025-02-18 21:38:43 +02:00 |
|
|
kijai
|
2997d6510e
|
add option to do cfg sequentially
|
2025-02-18 12:32:56 +02:00 |
|
|
kijai
|
e490745002
|
Update pipeline_hunyuan_video.py
|
2025-02-18 11:14:36 +02:00 |
|
|
kijai
|
e13d384ef7
|
small fixes
|
2025-02-18 11:01:04 +02:00 |
|
|
kijai
|
e063693a0c
|
Create hyvideo_skyreel_img2vid_testing_01.json
|
2025-02-18 05:15:31 +02:00 |
|
|
kijai
|
7b0c765b01
|
Update pipeline_hunyuan_video.py
|
2025-02-18 04:58:34 +02:00 |
|
|
kijai
|
63717f733a
|
cleanup
|
2025-02-18 04:30:05 +02:00 |
|
|
kijai
|
7a966b4da0
|
Merge branch 'main' of https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
|
2025-02-18 03:37:29 +02:00 |
|
|
kijai
|
3a6bebec64
|
testing for skyreel i2v
might not work proper yet
https://huggingface.co/Kijai/SkyReels-V1-Hunyuan_comfy/blob/main/skyreels_hunyuan_i2v_bf16.safetensors
|
2025-02-18 03:37:27 +02:00 |
|
|
Jukka Seppänen
|
ce58968da0
|
Merge pull request #340 from 2929Dance/fix-img2vid
Fix handling of cached input latents in img2vid
|
2025-02-08 21:02:17 +02:00 |
|
|
kijai
|
4fad5e349d
|
Standardize lora formats
|
2025-02-08 17:25:37 +02:00 |
|
|
kijai
|
46ce1149d6
|
Merge branch 'main' of https://github.com/kijai/ComfyUI-HunyuanVideoWrapper
|
2025-02-08 16:00:19 +02:00 |
|
|
kijai
|
f88d3fe03d
|
Don't scale custom noise...
|
2025-02-08 16:00:17 +02:00 |
|
|
Jukka Seppänen
|
9f50ed17d9
|
Update readme.md
|
2025-02-06 01:48:53 +02:00 |
|
|
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
|
43cb25a038
|
Update pipeline_hunyuan_video.py
|
2025-01-31 23:50:25 +02:00 |
|
|
kijai
|
0b9beb1884
|
Faster VAE decoding, fix leapfusion I2V flashing issue
|
2025-01-31 23:18:52 +02:00 |
|
|
kijai
|
1c966f0ee7
|
workaround for unload_all_models removing LoRA
|
2025-01-25 20:21:59 +02:00 |
|
|
kijai
|
30188f670a
|
Update pyproject.toml
|
2025-01-25 14:10:03 +02:00 |
|
|
kijai
|
863e15fe92
|
Update nodes.py
|
2025-01-25 14:09:44 +02:00 |
|
|
kijai
|
4c2a07c7cb
|
Update hyvideo_leapfusion_img2vid_example_01.json
|
2025-01-24 19:17:50 +02:00 |
|
|
kijai
|
72fe241ea6
|
Update pipeline_hunyuan_video.py
|
2025-01-24 17:57:35 +02:00 |
|
|
kijai
|
d4f102b7e8
|
Create hyvideo_leapfusion_img2vid_example_01.json
|
2025-01-24 17:39:31 +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
|
88823b79b7
|
Allow using custom noise
|
2025-01-19 00:41:19 +02:00 |
|
|
kijai
|
ea8ff71373
|
rf inversion fixes
|
2025-01-18 19:21:48 +02:00 |
|
|
Jukka Seppänen
|
be31a413a8
|
Merge pull request #255 from bezo97/enable-workflow-templates
Show example workflows in ComfyUI's template browser
|
2025-01-17 18:42:50 +02:00 |
|
|
kijai
|
fd2c196b48
|
Update posemb_layers.py
|
2025-01-17 17:10:56 +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 |
|
|
Jukka Seppänen
|
3acd21bec3
|
Merge pull request #203 from ComfyNodePRs/publish
Add Github Action for Publishing to Comfy Registry
|
2025-01-06 19:35:31 +02:00 |
|
|
Jukka Seppänen
|
45fbe46cd2
|
Merge pull request #204 from ComfyNodePRs/pyproject
Add pyproject.toml for Custom Node Registry
|
2025-01-06 19:35:10 +02:00 |
|
|
Jukka Seppänen
|
68b0305341
|
Update pyproject.toml
|
2025-01-06 19:34:55 +02:00 |
|
|
kijai
|
4fe87a3220
|
Some more schedulers
|
2025-01-06 19:17:46 +02:00 |
|
|
kijai
|
378b4a264d
|
Fix rf-inversion shift
|
2025-01-06 15:15:14 +02:00 |
|
|
kijai
|
e8e0ac4e56
|
support using comfy native VAE decoding
|
2025-01-06 14:58:05 +02:00 |
|
|
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 |
|