license: bigscience-openrail-m
datasets:
- proj-persona/PersonaHub
language:
- ru
metrics:
- bleu
library_name: flair
tags:
- art
ToonCrafter (512x320) Generative Cartoon Interpolation Model Card
ToonCrafter (512x320) is a video diffusion model that
takes in two still images as conditioning images and text prompt describing dynamics,
and generates interpolation videos from them.
Model Details
Model Description
ToonCrafter, a generative cartoon interpolation approach, aims to generate
short video clips (~2 seconds) from two conditioning images (starting frame and ending frame) and text prompt.
This model was trained to generate 16 video frames at a resolution of 512x320
given a context frame of the same resolution.
- Developed by: CUHK & Tencent AI Lab
- Funded by: CUHK & Tencent AI Lab
- Model type: Video Diffusion Model
- Finetuned from model: DynamiCrafter-interpolation (512x320)
Model Sources
For research purpose, we recommend our Github repository (https://github.com/ToonCrafter/ToonCrafter),
which includes detailed implementations.
- Repository: https://github.com/ToonCrafter/ToonCrafter
- Paper: https://arxiv.org/abs/2405.17933
- Project page: https://doubiiu.github.io/projects/ToonCrafter/
- Demo1: https://huggingface.co/spaces/Doubiiu/tooncrafter
- Demo2: https://replicate.com/fofr/tooncrafter
Uses
Feel free to use it under the Apache-2.0 license. Note that we don't have any official commercial product for ToonCrafter currently.
Limitations
- The generated videos are relatively short (2 seconds, FPS=8).
- The model cannot render legible text.
- The autoencoding part of the model is lossy, resulting in slight flickering artifacts.