Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
|
| 3 |
+
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
| 4 |
+
{}
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# DynamiCrafter (320x512) Generative Frame Interpolation / Looping Video Generation Model Card
|
| 8 |
+
## Generative Frame Interpolation
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
## Looping Video Generation
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 15 |
+
|
| 16 |
+
This is a video diffusion model that takes in a single or two still images as a conditioning <br> image and text prompt describing dynamics, and generates looping videos or interpolation from them.
|
| 17 |
+
|
| 18 |
+
## Model Details
|
| 19 |
+
|
| 20 |
+
### Model Description
|
| 21 |
+
|
| 22 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 23 |
+
|
| 24 |
+
DynamiCrafter, a (Text-)Image-to-Video/Image Animation approach, aims to generate <br>
|
| 25 |
+
short video clips (~2 seconds) from a conditioning image and text prompt.
|
| 26 |
+
|
| 27 |
+
This model was trained to generate 16 video frames at a resolution of 320x512 <br>
|
| 28 |
+
given a context frame of the same resolution.
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
- **Developed by:** CUHK & Tencent AI Lab
|
| 32 |
+
- **Funded by:** CUHK & Tencent AI Lab
|
| 33 |
+
- **Model type:** Generative frame interpolation and looping video generation
|
| 34 |
+
- **Finetuned from model:** VideoCrafter1 (320x512)
|
| 35 |
+
|
| 36 |
+
### Model Sources
|
| 37 |
+
|
| 38 |
+
<!-- Provide the basic links for the model. -->
|
| 39 |
+
For research purpose, we recommend our Github repository (https://github.com/Doubiiu/DynamiCrafter), <br>
|
| 40 |
+
which includes the detailed implementations.
|
| 41 |
+
- **Repository:** https://github.com/Doubiiu/DynamiCrafter
|
| 42 |
+
- **Paper:** https://arxiv.org/abs/2310.12190
|
| 43 |
+
|
| 44 |
+
## Uses
|
| 45 |
+
|
| 46 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 47 |
+
|
| 48 |
+
### Direct Use
|
| 49 |
+
|
| 50 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 51 |
+
|
| 52 |
+
We develop this repository for RESEARCH purposes, so it can only be used for personal/research/non-commercial purposes.
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
## Limitations
|
| 57 |
+
|
| 58 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 59 |
+
- The generated videos are relatively short (2 seconds, FPS=8).
|
| 60 |
+
- The model cannot render legible text.
|
| 61 |
+
- Faces and people in general may not be generated properly.
|
| 62 |
+
- The autoencoding part of the model is lossy, resulting in slight flickering artifacts.
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
## How to Get Started with the Model
|
| 67 |
+
|
| 68 |
+
Check out https://github.com/Doubiiu/DynamiCrafter
|
| 69 |
+
|