Update README.md
Browse files
README.md
CHANGED
@@ -1,11 +1,68 @@
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
library_name: diffusers
|
|
|
4 |
tags:
|
5 |
- text-to-video
|
|
|
6 |
---
|
|
|
7 |
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
-
This model
|
10 |
|
11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: creativeml-openrail-m
|
3 |
library_name: diffusers
|
4 |
+
inference: true
|
5 |
tags:
|
6 |
- text-to-video
|
7 |
+
- text-to-image
|
8 |
---
|
9 |
+
# ControlNet Canny Aracane Model Card
|
10 |
|
11 |
+
[Text2Video-Zero](https://arxiv.org/abs/2303.13439) is a zero-shot text to video generator. It can perform `zero-shot text-to-video generation`, `Video Instruct Pix2Pix` (instruction-guided video editing),
|
12 |
+
`text and pose conditional video generation`, `text and canny-edge conditional video generation`, and
|
13 |
+
`text, canny-edge and dreambooth conditional video generation`. For more information about this work,
|
14 |
+
please have a look at our [paper](https://arxiv.org/abs/2303.13439) and our demo: [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/PAIR/Text2Video-Zero)
|
15 |
+
Our [code](https://github.com/Picsart-AI-Research/Text2Video-Zero) works with any StableDiffusion base model.
|
16 |
|
17 |
+
This model provides [DreamBooth](https://arxiv.org/abs/2208.12242) weights for the `Arcane style` to be used with edge guidance (using [ControlNet](https://arxiv.org/abs/2302.05543)) in text2video zero.
|
18 |
|
19 |
+
|
20 |
+
## Weights for Text2Video-Zero
|
21 |
+
We converted the original weights into diffusers and made them usable for [ControlNet](https://arxiv.org/abs/2302.05543) with edge guidance using: https://github.com/lllyasviel/ControlNet/discussions/12.
|
22 |
+
|
23 |
+
|
24 |
+
### Model Details
|
25 |
+
- **Developed by:** Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, Zhangyang Wang, Shant Navasardyan and Humphrey Shi
|
26 |
+
- **Model type:** Dreambooth text-to-image and text-to-video generation model with edge control for text2video zero
|
27 |
+
- **Language(s):** English
|
28 |
+
- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license).
|
29 |
+
- **Model Description:** This is a model for [text2video zero](https://github.com/Picsart-AI-Research/Text2Video-Zero) with edge guidance and arcane style.
|
30 |
+
It can be used also with ControlNet in a text-to-image setup with edge guidance.
|
31 |
+
- **DreamBoth Keyword:** arcane style
|
32 |
+
- **Resources for more information:** [GitHub](https://github.com/Picsart-AI-Research/Text2Video-Zero), [Paper](https://arxiv.org/abs/2303.13439), [CIVITAI](https://civitai.com/models/23/arcane-diffusion).
|
33 |
+
- **Cite as:**
|
34 |
+
|
35 |
+
@article{text2video-zero,
|
36 |
+
title={Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators},
|
37 |
+
author={Khachatryan, Levon and Movsisyan, Andranik and Tadevosyan, Vahram and Henschel, Roberto and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey},
|
38 |
+
journal={arXiv preprint arXiv:2303.13439},
|
39 |
+
year={2023}
|
40 |
+
}
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
## Original Weights
|
46 |
+
The Dreambooth weights for the Arcane style were taken from [CIVITAI](https://civitai.com/models/23/arcane-diffusion).
|
47 |
+
|
48 |
+
### Model Details
|
49 |
+
- **Developed by:** Quiet_Joker (Username listed on CIVITAI)
|
50 |
+
- **Model type:** Dreambooth text-to-image generation model
|
51 |
+
- **Language(s):** English
|
52 |
+
- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license).
|
53 |
+
- **Model Description:** This is a model that was created using [DreamBooth](https://arxiv.org/abs/2208.12242) to generate images with Arcane style, based on text prompts.
|
54 |
+
- **DreamBoth Keyword:** arcane style
|
55 |
+
- **Resources for more information:** [CIVITAI](https://civitai.com/models/23/arcane-diffusion).
|
56 |
+
|
57 |
+
|
58 |
+
## Biases content acknowledgement:
|
59 |
+
Beware that Text2Video-Zero may output content that reinforces or exacerbates societal biases, as well as realistic faces, pornography, and violence. Text2Video-Zero in this demo is meant only for research purposes.
|
60 |
+
|
61 |
+
|
62 |
+
# Citation
|
63 |
+
@article{text2video-zero,
|
64 |
+
title={Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators},
|
65 |
+
author={Khachatryan, Levon and Movsisyan, Andranik and Tadevosyan, Vahram and Henschel, Roberto and Wang, Zhangyang and Navasardyan, Shant and Shi, Humphrey},
|
66 |
+
journal={arXiv preprint arXiv:2303.13439},
|
67 |
+
year={2023}
|
68 |
+
}
|