ComfyUI_StreamingT2V

ComfyUI_StreamingT2V 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

ComfyUI_StreamingT2V requires the following PyTorch-related packages: open-clip-torch, pytorch-lightning, rotary-embedding-torch, torchsde. Ensure your ComfyUI environment has these installed. Ensure your PyTorch installation matches your CUDA version (use torch.version.cuda to check).

To run ComfyUI_StreamingT2V, you need to install: accelerate, addict, albumentations, av, bitsandbytes, boto3, clip@ git+https://github.com/openai/CLIP.git@a1d071733d7111c9c014f024669f959182114e33, datasets, decord, diffusers, easydict, einops, fairscale, ffmpeg, gast, gdown, huggingface-hub, imageio, ipython, jsonargparse>=4.26.1, omegaconf, open-clip-torch, oss2, pandas, pibble, pytorch-lightning, raft, rich, rotary-embedding-torch, scikit-image, scikit-learn, scipy, seaborn, simplejson, sortedcontainers, torchsde, tqdm, transformers, xformers, yapf. You can install these using pip or add them to your requirements.txt file.

ComfyUI_StreamingT2V 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 ComfyUI_StreamingT2V: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/chaojie/ComfyUI_StreamingT2V, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.