ComfyUI-LivePortrait_v2

ComfyUI-LivePortrait_v2 requires a minimum of 4096MB (4.0GB) of VRAM for base operation. For optimal performance, a GPU with at least 8GB of VRAM is recommended. Low VRAM mode is not supported for this node.

✅ RTX 3060 (12GB): Yes, fully compatible with 6.8GB headroom. ✅ RTX 4070 (12GB): Yes, fully compatible with 6.8GB headroom. ✅ RTX 4070 Ti (16GB): Yes, fully compatible with 10.4GB headroom. ✅ RTX 4090 (24GB): Yes, fully compatible with 17.6GB headroom

On an RTX 3060 (12GB VRAM), ComfyUI-LivePortrait_v2 runs smoothly on an RTX 3060 (12GB) with 6.8GB of headroom. This is sufficient to run the node alongside standard SD 1.5 and SDXL workflows in full precision. On an RTX 4090 (24GB VRAM), the node runs with extreme headroom on an RTX 4090 (24GB) with 17.6GB of dedicated headroom. This allows you to combine the node with massive models (like FLUX.1 Dev, Schnell, or Hunyuan Video) in full precision (FP16) without any offload flags.

ComfyUI-LivePortrait_v2 requires the following PyTorch-related packages: open_clip_torch==2.26.1, pytorch-lightning==2.4.0, torch==2.3.0+cu121, torchaudio==2.3.0+cu121, torchmetrics==1.5.1, torchscale==0.3.0, torchsde==0.2.6, torchvision==0.18.0+cu121. Ensure your ComfyUI environment has these installed. CUDA 12.1 is required. This works best with RTX 3000 and 4000 series GPUs.

To run ComfyUI-LivePortrait_v2, you need to install: absl-py==2.1.0, accelerate==0.34.2, addict==2.4.0, aggdraw==1.3.19, aiofiles==23.2.1, aiohappyeyeballs==2.4.0, aiohttp==3.10.5, aioresponses==0.7.6, aiosignal==1.3.1, albucore==0.0.14, albumentations==1.4.10, altair==5.4.1, annotated-types==0.7.0, anthropic==0.34.2, antlr4-python3-runtime==4.9.3, anyio==4.4.0, apscheduler==3.10.1, arrow==1.3.0, async-timeout==4.0.3, attrs==24.2.0, av==12.3.0, awscli==1.33.44, backoff==2.2.1, basicsr==1.4.2, beautifulsoup4==4.12.3, binaryornot==0.4.4, bitsandbytes==0.44.1, blend_modes==2.1.0, blind-watermark==0.4.4, boto3==1.34.123, botocore==1.34.162, cachetools==5.5.0, certifi==2024.8.30, cffi==1.17.0, cfgv==3.4.0, chardet==5.2.0, charset-normalizer==3.3.2, click==8.1.7, clip-interrogator==0.6.0, cmake==3.30.2, color-matcher==0.5.0, colorama==0.4.4, coloredlogs==15.0.1, colorlog==6.8.2, colour-science==0.4.4, contourpy==1.3.0, cookiecutter==2.6.0, cryptography==43.0.0, cssselect2==0.7.0, cstr@ git+https://github.com/WASasquatch/cstr@0520c29a18a7a869a6e5983861d6f7a4c86f8e9b, ctranslate2==4.5.0, cycler==0.12.1, cython==3.0.0, dataclasses-json==0.6.7, ddt==1.7.2, decord==0.6.0, deepspeed==0.15.1, defusedxml==0.7.1, deprecated==1.2.14, diffusers==0.31.0, dill==0.3.8, distlib==0.3.9, distro==1.9.0, dlib@ file:///home/conda/feedstock_root/build_artifacts/dlib-split_1726093008991/work, docker==6.1.3, docker-pycreds==0.4.0, docopt==0.6.2, docstring_parser==0.16, docutils==0.16, easydict==1.13, einops==0.8.0, embreex==2.17.7.post5, exceptiongroup==1.2.2, fairscale==0.4.13, fal_client==0.5.2, fastapi==0.110.3, faster-whisper==1.0.3, ffmpeg==1.4, ffmpeg-python==0.2.0, ffmpy@ git+https://github.com/WASasquatch/ffmpy.git@f000737698b387ffaeab7cd871b0e9185811230d, ffprobe==0.5, filelock==3.13.1, flatbuffers==24.3.25, flet==0.24.1, flet-core==0.24.1, flet-runtime==0.24.1, fonttools==4.53.1, frozenlist==1.4.1, fsspec==2024.2.0, ftfy==6.2.3, future==1.0.0, fvcore==0.1.5.post20221221, gdown==5.2.0, gitdb==4.0.11, gitpython==3.1.43, gputil==1.4.0, gradio==4.37.1, gradio_client==1.0.2, grpcio==1.66.1, grpcio-status==1.66.1, h11==0.14.0, hjson==3.1.0, httpcore==1.0.5, httplib2==0.22.0, httptools==0.6.1, httpx==0.27.2, httpx-sse==0.4.0, huggingface-hub==0.23.4, humanfriendly==10.0, hydra-core==1.3.2, identify==2.6.1, idna==3.8, imageio==2.34.2, imageio-ffmpeg==0.5.1, img2texture@ git+https://github.com/WASasquatch/img2texture.git@d6159abea44a0b2cf77454d3d46962c8b21eb9d3, importlib_metadata==8.5.0, importlib_resources==6.4.4, inference-cli==0.20.1, inference-gpu==0.20.1, iniconfig==2.0.0, insightface==0.7.3, instructor==1.6.3, iopath==0.1.10, jax==0.4.31, jaxlib==0.4.31, jinja2==3.1.4, jiter==0.5.0, jmespath==1.0.1, joblib==1.4.2, json_repair==0.30.0, jsonschema==4.23.0, jsonschema-specifications==2023.12.1, kaldi-native-fbank==1.20.0, kiwisolver==1.4.5, kornia==0.7.3, kornia_rs==0.1.5, lark-parser==0.12.0, lazy_loader==0.4, lightning-utilities==0.11.8, llvmlite==0.43.0, lmdb==1.4.1, loguru==0.7.2, loralib==0.1.2, lxml==5.3.0, manifold3d==2.5.1, mapbox_earcut==1.0.2, markdown==3.7, markdown-it-py==3.0.0, markupsafe==2.1.5, marshmallow==3.22.0, matplotlib==3.9.2, matrix-client==0.4.0, mdurl==0.1.2, mediapipe==0.10.15, ml-dtypes==0.4.0, mpmath==1.3.0, mss==9.0.2, multidict==6.0.5, multiscaledeformableattention==1.0, mypy-extensions==1.0.0, narwhals==1.6.0, natsort==8.4.0, networkx==3.2.1, ninja==1.11.1.1, nodeenv==1.9.1, numba==0.60.0, numpy==1.26.4, nvidia-cublas-cu12==12.1.3.1, nvidia-cuda-cupti-cu12==12.1.105, nvidia-cuda-nvrtc-cu12==12.1.105, nvidia-cuda-runtime-cu12==12.1.105, nvidia-cudnn-cu12==8.9.2.26, nvidia-cufft-cu12==11.0.2.54, nvidia-curand-cu12==10.3.2.106, nvidia-cusolver-cu12==11.4.5.107, nvidia-cusparse-cu12==12.1.0.106, nvidia-ml-py==12.560.30, nvidia-nccl-cu12==2.20.5, nvidia-nvjitlink-cu12==12.1.105, nvidia-nvtx-cu12==12.1.105, oauthlib==3.2.2, omegaconf==2.3.0, onnx==1.16.1, onnxruntime==1.19.2, onnxruntime-gpu==1.15.1, open_clip_torch==2.26.1, openai==1.52.1, opencv-contrib-python==4.10.0.84, opencv-python==4.10.0.84, opencv-python-headless==4.10.0.84, opt-einsum==3.3.0, orjson==3.10.7, packaging==24.1, pandas==2.2.2, peft==0.12.0, pendulum==3.0.0, piexif==1.1.3, pilgram==1.2.1, pillow==10.4.0, pixeloe==0.0.10, platformdirs==4.2.2, pluggy==1.5.0, pooch==1.8.2, portalocker==2.10.1, positional-encodings==6.0.3, pre_commit==4.0.1, prettytable==3.11.0, prometheus-fastapi-instrumentator==6.0.0, prometheus_client==0.21.0, proto-plus==1.24.0, protobuf==5.28.3, psd-tools==1.10.0, psutil==5.9.8, pulp==2.9.0, py-cpuinfo==9.0.0, pyasn1==0.6.1, pyasn1_modules==0.4.1, pybase64==1.4.0, pycollada==0.8, pycparser==2.22, pydantic==2.8.2, pydantic-settings==2.5.2, pydantic_core==2.20.1, pydot==3.0.2, pydub==0.25.1, pygithub==2.4.0, pygments==2.18.0, pyjwt==2.9.0, pykalman==0.9.7, pymatting==1.1.12, pynacl==1.5.0, pyopenssl==24.2.1, pyparsing==3.1.4, pypng==0.20220715.0, pysocks==1.7.1, pytest==8.3.3, pytest-asyncio==0.21.1, python-dateutil==2.9.0.post0, python-dotenv==1.0.1, python-multipart==0.0.9, python-slugify==8.0.4, pytorch-lightning==2.4.0, pytz==2024.1, pywavelets==1.7.0, pyyaml==6.0.1, pyzbar==0.1.9, qrcode==7.4.2, redis==5.0.8, referencing==0.35.1, regex==2024.7.24, rembg==2.0.59, repath==0.9.0, reportlab==4.2.5, requests==2.31.0, requests-file==2.1.0, requests-toolbelt==1.0.0, rf-clip==1.1, rich==13.9.3, rpds-py==0.20.0, rsa==4.7.2, rtree==1.3.0, ruff==0.6.3, s3transfer==0.10.2, safetensors==0.4.4, scenedetect==0.6.4, scikit-image==0.24.0, scikit-learn==1.5.1, scipy==1.13.1, seaborn==0.13.2, segment-anything==1.0, semantic-version==2.10.0, sensevoice-onnx@ git+https://github.com/shadowcz007/SenseVoice-python.git@43f6cf1531e7e4a7d7507d37fbc9b0fb169166ab, sentencepiece==0.2.0, sentry-sdk==2.14.0, setproctitle==1.3.3, shapely==2.0.6, shellingham==1.5.4, shtab==1.7.1, simpleeval==1.0.0, six==1.16.0, skypilot==0.5.0, smmap==5.0.1, sniffio==1.3.1, sounddevice==0.5.0, soundfile==0.12.1, soupsieve==2.6, spaces==0.30.3, spandrel==0.3.4, starlette==0.37.2, structlog==24.4.0, supervision==0.22.0, svg.path==6.3, svglib==1.5.1, swarm@ git+https://github.com/openai/swarm.git@9db581cecaacea0d46a933d6453c312b034dbf47, sympy==1.12, tabulate==0.9.0, tb-nightly==2.18.0a20240911, tenacity==9.0.0, tensorboard-data-server==0.7.2, termcolor==2.5.0, text-unidecode==1.3, threadpoolctl==3.5.0, tifffile==2024.8.30, time-machine==2.15.0, timm==0.6.13, tinycss2==1.3.0, tldextract==5.1.2, tokenizers==0.19.1, tomli==2.0.1, tomlkit==0.12.0, torch==2.3.0+cu121, torchaudio==2.3.0+cu121, torchmetrics==1.5.1, torchscale==0.3.0, torchsde==0.2.6, torchvision==0.18.0+cu121, tqdm==4.66.4, trampoline==0.1.2, transformers==4.44.2, transparent-background==1.3.2, trimesh==4.4.9, triton==2.3.0, typer==0.12.5, typer-config==1.4.0, types-python-dateutil==2.9.0.20240821, typing-inspect==0.9.0, typing_extensions==4.12.2, tyro==0.8.5, tzdata==2024.1, tzlocal==5.2, ultralytics==8.2.102, ultralytics-thop==2.0.8, uritemplate==4.1.1, urllib3==2.2.3, uvicorn==0.30.6, uvloop==0.20.0, vhacdx==0.0.8.post1, virtualenv==20.27.0, wandb==0.18.0, watchdog==4.0.2, watchfiles==0.24.0, wcwidth==0.2.13, webencodings==0.5.1, websocket-client==1.8.0, websockets==11.0.3, werkzeug==3.0.4, wget==3.2, wrapt==1.16.0, xatlas==0.0.9, xxhash==3.5.0, yacs==0.1.8, yapf==0.40.2, yarl==1.9.7, zipp==3.20.1, zxing-cpp==2.2.0. You can install these using pip or add them to your requirements.txt file.

To install ComfyUI-LivePortrait_v2: (1) Navigate to your ComfyUI/custom_nodes directory, (2) Clone the repository: git clone https://github.com/VangengLab/ComfyUI-LivePortrait_v2, (3) Install dependencies: pip install -r requirements.txt (if present), (4) Restart ComfyUI. Alternatively, use ComfyUI Manager for one-click installation.