BAAI
/

PhyscalX commited on
Commit
948bafe
1 Parent(s): 659b73e

Update model type

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -10,11 +10,11 @@ tags:
10
 
11
  ## Model Details
12
  - **Developed by:** BAAI
13
- - **Model type:** Masked Autoregressive Text-to-Image Generation Model
14
  - **Model size:** 645M
15
  - **Model precision:** torch.float16 (FP16)
16
  - **Model resolution:** 512x512
17
- - **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Masked Autoregressive (MAR)](https://arxiv.org/abs/2406.11838) diffusion model that uses a pretrained text encoder ([Phi-2](https://huggingface.co/microsoft/phi-2)) and one VAE image tokenizer ([SD-VAE](https://huggingface.co/stabilityai/sd-vae-ft-mse)).
18
  - **Model License:** [Apache 2.0 License](LICENSE)
19
  - **Resources for more information:** [GitHub Repository](https://github.com/baaivision/NOVA).
20
 
 
10
 
11
  ## Model Details
12
  - **Developed by:** BAAI
13
+ - **Model type:** Non-quantized Autoregressive Text-to-Image Generation Model
14
  - **Model size:** 645M
15
  - **Model precision:** torch.float16 (FP16)
16
  - **Model resolution:** 512x512
17
+ - **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Non-quantized Video Autoregressive (NOVA)](https://arxiv.org/abs/2412.14169) diffusion model that uses a pretrained text encoder ([Phi-2](https://huggingface.co/microsoft/phi-2)) and one VAE image tokenizer ([SD-VAE](https://huggingface.co/stabilityai/sd-vae-ft-mse)).
18
  - **Model License:** [Apache 2.0 License](LICENSE)
19
  - **Resources for more information:** [GitHub Repository](https://github.com/baaivision/NOVA).
20