IMAGDressing-ComfyUI

IMAGDressing-ComfyUI requires a minimum of 128MB (0.1GB) of VRAM for base operation. For optimal performance, a GPU with at least 4GB of VRAM is recommended. This node supports low VRAM mode for resource-constrained setups.

✅ RTX 3060 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 10.7GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 14.3GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 21.5GB headroom

To run IMAGDressing-ComfyUI, you need to install: accelerate, aiohttp, aiosignal, annotated-types, async-timeout, attrs, bitsandbytes, certifi, charset-normalizer, datasets, deepspeed;sys_platform!='win32', diffusers, dill, einops, filelock, frozenlist, fsspec, hjson, huggingface-hub, idna, importlib_metadata, insightface, jinja2, markupsafe, mpmath, multidict, multiprocess, networkx, ninja, numpy, onnxruntime;sys_platform == "win32", onnxruntime-gpu;sys_platform != "win32", opencv-python, pandas, peft, pillow, psutil, py-cpuinfo, pyarrow, pyarrow-hotfix, pydantic, pydantic_core, pynvml, python-dateutil, pytz, pyyaml, regex, requests, safetensors, six, sympy, tokenizers, tqdm, transformers, typing_extensions, tzdata, urllib3, xxhash, yarl, zipp. You can install these using pip or add them to your requirements.txt file.

IMAGDressing-ComfyUI supports low VRAM mode. To reduce memory usage: (1) Enable --lowvram or --medvram flags in ComfyUI, (2) Reduce batch size to 1, (3) Use fp16 or fp8 precision if supported, (4) Close other GPU applications.

To install IMAGDressing-ComfyUI: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/AIFSH/IMAGDressing-ComfyUI, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.