0110e2ea42
fix resolution issue
2025-02-04 21:56:21 -05:00
ebf873e4b1
wip
2025-02-04 18:46:48 -05:00
193c23590f
new inference script
2025-02-04 18:21:40 -05:00
41dd8fce85
Modify data prep script to handle single video w/ predictable pathing
2025-02-04 16:28:59 -05:00
afe7e71924
install
2025-02-03 20:06:07 -05:00
046ab789c0
Add Animate-X (see details)
...
https://lucaria-academy.github.io/Animate-X/
https://github.com/antgroup/animate-x
@ fdc80909f911d8e487cb4e6847f2e4c6501b62af
2025-02-03 18:22:05 -05:00
5ab5b1c036
add UniAnimate (see notes)
...
@ d7814fa44a0a1154524b92fce0e3133a2604d333
https://github.com/ali-vilab/UniAnimate
2025-02-03 18:21:13 -05:00
94daa7d1e3
copy over starting frames
2025-02-02 04:35:07 -05:00
3a940b0bc8
fps parameter
2025-02-02 03:40:24 -05:00
0ec0ed4c7e
stable-animator: string wrapping fix
2025-01-24 21:43:43 +05:30
256b018047
stable-animator: pin transformers version
2025-01-24 19:47:56 +05:30
5e012f3139
bugfix inference, convert to mp4
2025-01-23 23:56:14 -05:00
089c73d512
rename another command line arg
2025-01-21 22:55:22 -05:00
bdb087fc7e
change output dir param name
2025-01-21 22:53:35 -05:00
37e4d92deb
reference script
2025-01-21 18:51:19 -05:00
63012c2a98
add github action
2025-01-20 22:08:17 -05:00
ff1acb19f6
fix docker image
2025-01-20 22:06:26 -05:00
97e7f858d5
don't invoke git-lfs model install in container
2025-01-20 21:35:49 -05:00
713d69f390
accept pose videos
2025-01-20 02:26:37 -05:00
5712d89e73
reuse base inference script
2025-01-19 22:22:16 -05:00
7400f2876a
wip containerization
2025-01-19 20:12:09 -05:00
f912a79914
Add StableAnimator @ 0f3d85ad217c0d3edec89e310bb34c3ecb9eaf9b
...
https://github.com/Francis-Rings/StableAnimator/commit/0f3d85ad217c0d3edec89e310bb34c3ecb9eaf9b
2025-01-17 18:52:50 -05:00
46302b7c0c
seed-vc: Use openai/whisper-small ( #61 )
...
Use openai/whisper-small as aa a workaround for whisper-large-v3 being unavailable and newer whisper versions being incompatible as a hotfix
2024-12-04 18:24:59 +05:30
8785206e14
add cogvideo custom node
2024-11-14 17:28:13 +05:30
e95ea00436
add support for cogvide
2024-11-14 17:19:55 +05:30
7e12c7c3a5
seed-vc: change output name, put examples in the container, use cuda 12.1
2024-10-23 16:56:13 +05:30
7d5fd4f029
add seed-vc model ( #60 )
...
* init seed-vc
* seed-vc workflow
* put seed-vc in the right dir
2024-10-22 18:40:01 +05:30
1b8477b4b1
f5-tts build: more stuff to make inference-cli.py to work with actions
2024-10-21 20:30:44 +05:30
b0b95c4d9d
add tests dir
2024-10-21 19:58:36 +05:30
e7cce4751d
f5 tts - remove tests/ from .gitignore
2024-10-21 19:58:01 +05:30
da1128478b
f5 tts docker workflow - list docker context dir
2024-10-21 19:51:26 +05:30
3c570d38ef
f5-tts docker workflow - try free diskspace action
2024-10-21 19:29:11 +05:30
9153bb9ba9
Update docker-publish-f5-tts.yml
2024-10-21 19:23:01 +05:30
4a36f32809
fixup check github runner diskspace
2024-10-21 19:11:13 +05:30
e858dc5d31
check diskspace on github runner
2024-10-21 19:05:00 +05:30
9fd8912e95
f5-tts: remove HF_DATASET_CACHE from docker build
2024-10-21 18:59:46 +05:30
b9c2c57690
allow manually triggering f5-tts image publish
2024-10-21 18:42:11 +05:30
66421fcb87
Update docker-publish-f5-tts.yml
2024-10-21 18:38:21 +05:30
c2a90ff423
Update docker-publish-f5-tts.yml
2024-10-21 18:32:36 +05:30
b9c516e8f0
F5 tts ( #59 )
...
* init tts/F5-TTS
* epic hax to download ckpts
* clear default reference audio/text from inference vars
* allow blank inputs for inference-cli to just pull checkpoints without running inference
* f5-tts github workflow to publish docker images
2024-10-21 18:25:28 +05:30
e51123956f
add render.storyteller.ai to preview server CORS
2024-10-06 17:50:00 -04:00
183817f064
comfy: fix cinematic mode
2024-09-20 18:50:36 +05:30
0fdf46a885
facefusion: minor updates to runner
2024-09-05 19:19:13 +05:30
98c8b44a45
Update cleaner.py
...
Remove unnecessary loops
2024-08-14 22:16:21 +05:30
79a70a1acf
GPT-SoVITS: Update base code and infer script
2024-08-13 18:46:03 +05:30
d190b34895
comfy runner: catch requests exceptions appropriately
2024-08-09 18:37:57 +05:30
24f7e6ebcb
comfy: log where rust can find them
2024-08-09 16:26:45 +05:30
9d2b09b492
live portraits: more resilient to comfy errors
2024-08-08 18:05:19 +05:30
e672768c6f
live portrait: accept larger messages from comfy
2024-08-08 15:39:43 +05:30
9aebadf790
Update the base code
2024-08-08 09:59:00 +05:30
Brandon Thomas