forked from Wan-Video/Wan2.1
-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Expand file tree
/
Copy pathrequirements.txt
More file actions
114 lines (106 loc) · 2.9 KB
/
Copy pathrequirements.txt
File metadata and controls
114 lines (106 loc) · 2.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
--extra-index-url https://aiinfra.pkgs.visualstudio.com/PublicPackages/_packaging/ort-cuda-13-nightly/pypi/simple/
mmgp==3.7.14
# Core AI stack
diffusers==0.36.0
transformers==4.54.0 #4.53.1
tokenizers>=0.20.3
accelerate>=1.1.1
tqdm
imageio
imageio-ffmpeg
einops
rotary-embedding-torch>=0.5.3
sentencepiece
tiktoken
fugashi>=1.2.0
unidic-lite>=1.0.0
open_clip_torch>=2.29.0
numpy==2.1.2
num2words==0.5.14
# Video & media
moviepy==1.0.3
av
ffmpeg-python
pygame>=2.1.0
sounddevice>=0.4.0
soundfile
mutagen
pyloudnorm
librosa==0.11.0
speechbrain==1.0.3
openai-whisper==20250625
audio-separator==0.36.1
pyannote.audio==3.3.2
sherpa-onnx==1.13.2
torchcodec==0.10.0
einshape==1.0
jax
# Flax/Linen micro-subset is vendored under postprocessing/prismaudio/vendor/flax
# for PrismAudio VideoPrism; keeping it out of pip avoids orbax-checkpoint.
# UI & interaction
gradio==5.29.0
dashscope
loguru
s3tokenizer
conformer==0.3.2
spacy_pkuseg
spacy
gradio_rangeslider
# Vision & segmentation
opencv-python>=4.12.0.88
ultralytics
scipy
pycocotools
segment-anything
rembg[gpu]==2.0.65; platform_system != "Darwin"
rembg==2.0.65; platform_system == "Darwin"
onnxruntime-gpu==1.22.0; python_version < "3.11" and platform_system != "Darwin"
onnxruntime-gpu==1.25.0.dev20260210001; python_version >= "3.11" and platform_system != "Darwin"
onnxruntime>=1.22.0; platform_system == "Darwin"
decord; sys_platform != "darwin"
timm
iopath>=0.1.10
insightface @ https://github.com/deepbeepmeep/insightface/releases/download/insightface/insightface-0.7.3-cp310-cp310-win_amd64.whl ; sys_platform == "win32" and python_version == "3.10"
insightface @ https://github.com/deepbeepmeep/insightface/releases/download/insightface/insightface-0.7.3-cp311-cp311-win_amd64.whl ; sys_platform == "win32" and python_version == "3.11"
insightface @ https://github.com/deepbeepmeep/insightface/releases/download/insightface/insightface-0.7.3-cp312-cp312-win_amd64.whl ; sys_platform == "win32" and python_version == "3.12"
insightface==0.7.3 ; sys_platform == "linux"
facexlib==0.3.0
taichi
vector_quantize_pytorch==1.27.19
# chumpy wheel hosted on GitHub to avoid sdist build isolation issue
chumpy @ https://github.com/deepbeepmeep/chumpy/releases/download/v0.71/chumpy-0.71-py3-none-any.whl
smplfitter @ https://github.com/deepbeepmeep/smplfitter/releases/download/v0.2.10/smplfitter-0.2.10-py3-none-any.whl
# Config & orchestration
omegaconf
hydra-core
easydict
pydantic==2.10.6
mcp==1.10.1
# Math & modeling
torchdiffeq>=0.2.5
tensordict>=0.6.1
peft==0.17.0 # 0.15.0
vector-quantize-pytorch
matplotlib
gguf==0.17.1
flash-linear-attention==0.4.1
# Utilities
ftfy
piexif
nvidia-ml-py
misaki
phonemizer-fork
espeakng-loader
gitdb==4.0.12
gitpython==3.1.45
stringzilla==4.0.14
xxhash
munch
wetext==0.1.2
markdown
apprise==1.12.0
keyring==25.7.0
# Optional / commented out
# transformers==4.46.3 # for llamallava pre-patch
# rembg==2.0.65 # non-GPU fallback
huggingface_hub[hf_xet]