ComfyUI/requirements.txt
doctorpangloss 8741cb3ce8 LLM support in ComfyUI
- Currently uses `transformers`
 - Supports model management and correctly loading and unloading models
   based on what your machine can support
 - Includes a Text Diffusers 2 workflow to demonstrate text rendering in
   SD1.5
2024-05-14 17:30:23 -07:00

52 lines
954 B
Plaintext

torch
torchvision
torchdiffeq>=0.2.3
torchsde>=0.2.6
einops>=0.6.0
open-clip-torch>=2.16.0
transformers>=4.29.1
peft
torchinfo
fschat[model_worker]
safetensors>=0.3.0
bitsandbytes
pytorch-lightning>=2.0.0
aiohttp>=3.8.4
accelerate>=0.25.0
pyyaml>=6.0
scikit-image>=0.20.0
jsonmerge>=1.9.0
clean-fid>=0.1.35
clip @ git+https://github.com/openai/CLIP.git@main#egg=clip
resize-right>=0.0.2
opencv-python-headless>=4.9.0.80
albumentations>=1.3.0
aiofiles>=23.1.0
frozendict>=2.3.6
python-dateutil>=2.8.2
importlib_resources
Pillow
scipy
tqdm
protobuf
psutil
ConfigArgParse
aio-pika
pyjwt[crypto]
kornia>=0.7.1
mpmath>=1.0,!=1.4.0a0
huggingface_hub
lazy-object-proxy
can_ada
fsspec
natsort
OpenEXR
opentelemetry-distro
opentelemetry-exporter-otlp
opentelemetry-propagator-jaeger
opentelemetry-instrumentation
opentelemetry-util-http
opentelemetry-instrumentation-aio-pika
opentelemetry-instrumentation-requests
opentelemetry-semantic-conventions
wrapt>=1.16.0