Update README.md
Browse files
README.md
CHANGED
|
@@ -33,5 +33,18 @@ We further demonstrate the superiority of I2I priors over T2I priors on some tex
|
|
| 33 |
## 🚀 Model Structure
|
| 34 |
|
| 35 |
|
|
|
|
| 36 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
|
|
|
| 33 |
## 🚀 Model Structure
|
| 34 |
|
| 35 |
|
| 36 |
+
[Lumos](https://arxiv.org/pdf/2412.07767) consists of transformer blocks for latent diffusion, which is applied for various visual generative tasks such as text-to-image, image-to-3D, and image-to-video generation.
|
| 37 |
|
| 38 |
+
Source code is available at https://github.com/xiaomabufei/lumos.
|
| 39 |
+
|
| 40 |
+
### Model Description
|
| 41 |
+
|
| 42 |
+
- **Developed by:** Lumos-I2I
|
| 43 |
+
- **Model type:** Diffusion-Transformer-based generative model
|
| 44 |
+
- **License:** [CreativeML Open RAIL++-M License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md)
|
| 45 |
+
- **Model Description:** This is a model that can be used to generate and modify images based on image prompt.
|
| 46 |
+
It is a [Transformer Latent Diffusion Model](https://arxiv.org/abs/2310.00426) that uses one fixed, pretrained vision encoders ([DINO](
|
| 47 |
+
https://dl.fbaipublicfiles.com/dino/dino_vitbase16_pretrain/dino_vitbase16_pretrain.pth))
|
| 48 |
+
and one latent feature encoder ([VAE](https://arxiv.org/abs/2112.10752)).
|
| 49 |
+
- **Resources for more information:** Check out our [GitHub Repository](https://github.com/xiaomabufei/lumos) and the [Lumos report on arXiv](https://arxiv.org/pdf/2412.07767).
|
| 50 |
|