LivePortrait vs ToonCrafter
LivePortrait
liveportrait.github.ioToonCrafter
doubiiu.github.ioSide by side
| Figure | LivePortrait | ToonCrafter |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | Yes | Yes |
| macOS | Yes | — |
| Linux | Yes | — |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 0 |
| Spec score · Image-to-Video Generators | 7.9 (#11) | 6.7 (#20) |
| integrations | Community resources include FaceFusion, ComfyUI nodes, a Stable Diffusion WebUI extension, Replicate, FAL, Poe, and Hugging Face Spaces. | The repository lists community implementations or support for ComfyUI, Colab, and Windows. |
| Local use | The repository provides inference code, pretrained models, and a Gradio interface for local use. | The repository provides command-line inference and a local Gradio demo. |
| Purpose | LivePortrait animates a portrait from a still image using facial expressions and head pose from a driving video, audio, text, or generated motion. | ToonCrafter interpolates two cartoon images using pretrained image-to-video diffusion priors. |
In their own words
LivePortrait
LivePortrait creates portrait video from a single image, using motion from video, audio, text, or generation. It also supports editing portrait video using a source video and a driving video. Stitching and eye and lip retargeting controls provide ways to adjust animation. The project supplies inference code, pretrained models, and a Gradio interface for local use, as well as a demo hosted on Hugging Face Spaces. Its PyTorch implementation is released under the MIT License, and the project reports generation speed of 12.8 ms on an RTX 4090 GPU with PyTorch. Human-mode instructions cover Linux, Windows, and Apple Silicon macOS; Intel macOS is untested. Animal models can animate cats, dogs, and pandas using human-driven motion, but animal mode is tested only on Linux and Windows with an NVIDIA GPU and is unsupported on macOS. Local setup requires git, conda, FFmpeg, Python 3.10, and downloaded pretrained weights. Commercial users must replace the included InsightFace detection models. Maintainers warn of possible deepfake misuse and visual artifacts.
ToonCrafter
ToonCrafter has no write-up on Specifiction yet; its figures are above.