| | --- |
| | pipeline_tag: image-to-video |
| | --- |
| | |
| | # DynamiCrafter (256x256) (text-)Image-to-Video/Image Animation Model Card |
| |  |
| | <!-- Provide a quick summary of what the model is/does. --> |
| |
|
| | DynamiCrafter (256x256) (Text-)Image-to-Video is a video diffusion model that <br> takes in a still image as a conditioning image and text prompt describing dynamics,<br> and generates videos from it. |
| |
|
| | ## Model Details |
| |
|
| | ### Model Description |
| |
|
| | <!-- Provide a longer summary of what this model is. --> |
| |
|
| | DynamiCrafter, a (Text-)Image-to-Video/Image Animation approach, aims to generate <br> |
| | short video clips (~2 seconds) from a conditioning image and text prompt. |
| |
|
| | This model was trained to generate 16 video frames at a resolution of 256x256 <br> |
| | given a context frame of the same resolution. |
| |
|
| |
|
| | - **Developed by:** CUHK & Tencent AI Lab |
| | - **Funded by:** CUHK & Tencent AI Lab |
| | - **Model type:** Generative (text-)image-to-video model |
| | - **Finetuned from model:** VideoCrafter1 (256x256) |
| |
|
| | ### Model Sources |
| |
|
| | <!-- Provide the basic links for the model. --> |
| | For research purpose, we recommend our Github repository (https://github.com/Doubiiu/DynamiCrafter), <br> |
| | which includes the detailed implementations. |
| | - **Repository:** https://github.com/Doubiiu/DynamiCrafter |
| | - **Paper:** https://arxiv.org/abs/2310.12190 |
| | ## Uses |
| |
|
| | <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> |
| |
|
| | ### Direct Use |
| |
|
| | <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> |
| |
|
| | We develop this repository for RESEARCH purposes, so it can only be used for personal/research/non-commercial purposes. |
| |
|
| |
|
| |
|
| | ## Limitations |
| |
|
| | <!-- This section is meant to convey both technical and sociotechnical limitations. --> |
| | - The generated videos are relatively short (2 seconds, FPS=8). |
| | - The model cannot render legible text. |
| | - Faces and people in general may not be generated properly. |
| | - The autoencoding part of the model is lossy, resulting in slight flickering artifacts. |
| |
|
| |
|
| |
|
| | ## How to Get Started with the Model |
| |
|
| | Check out https://github.com/Doubiiu/DynamiCrafter |
