amd
/

Text-to-Image
Diffusers
Safetensors
art
akasharidas commited on
Commit
ab88d76
·
verified ·
1 Parent(s): b613948

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,7 +14,7 @@ tags:
14
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6355aded9c72a7e742f341a4/J-hy3Wb2lYA3d8mDGRPw-.png)
15
 
16
  ## Introduction
17
- Nitro-T is a set of text-to-image diffusion models focused on highly efficient training. Our models achieve competitive scores on image generation benchmarks compared to previous models focused on efficient training while requiring less than 1 day of training from scratch on 32 AMD Instinct™ MI300X GPUs. The release consists of:
18
 
19
  * [Nitro-T-0.6B](https://huggingface.co/amd/Nitro-T-0.6B): a 512px DiT-based model
20
  * [Nitro-T-1.2B](https://huggingface.co/amd/Nitro-T-1.2B): a 1024px MMDiT-based model
 
14
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6355aded9c72a7e742f341a4/J-hy3Wb2lYA3d8mDGRPw-.png)
15
 
16
  ## Introduction
17
+ Nitro-T is a family of text-to-image diffusion models focused on highly efficient training. Our models achieve competitive scores on image generation benchmarks compared to previous models focused on efficient training while requiring less than 1 day of training from scratch on 32 AMD Instinct™ MI300X GPUs. The release consists of:
18
 
19
  * [Nitro-T-0.6B](https://huggingface.co/amd/Nitro-T-0.6B): a 512px DiT-based model
20
  * [Nitro-T-1.2B](https://huggingface.co/amd/Nitro-T-1.2B): a 1024px MMDiT-based model