Text-to-Image
Transformers
English
SupraDiT
feature-extraction
small
supra
image
flux
img
t2i
from scratch
custom_code
Instructions to use SupraLabs/Supra2-IMG with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SupraLabs/Supra2-IMG with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SupraLabs/Supra2-IMG", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Fix parameter count inconsistency in README
#2
by BananaMindBot - opened
README.md
CHANGED
|
@@ -42,7 +42,7 @@ tags:
|
|
| 42 |
The model is a tiny diffusion transformer (DiT) with ~105M parameters.
|
| 43 |
|
| 44 |
- Pipeline: text-to-image
|
| 45 |
-
- Parameter Count: 104.
|
| 46 |
- Encoder: frozen [Flan-T5-Base](https://huggingface.co/google/flan-t5-base)
|
| 47 |
- VAE: [SD-VAE-FT-MSE](https://huggingface.co/stabilityai/sd-vae-ft-mse)
|
| 48 |
- Image resolution: 256²
|
|
@@ -138,8 +138,6 @@ Generating: ...
|
|
| 138 |
|
| 139 |

|
| 140 |
|
| 141 |
-
---
|
| 142 |
-
|
| 143 |
## Acknowledgments
|
| 144 |
|
| 145 |
- Thank you, FLUX-Reason-6M team, for proving the [LucasFang/FLUX-Reason-6M](https://huggingface.co/datasets/LucasFang/FLUX-Reason-6M) dataset. Without **your** work, this would never be possible!
|
|
@@ -151,4 +149,4 @@ Generating: ...
|
|
| 151 |
## What's next
|
| 152 |
|
| 153 |
We will keep improving Supra2-IMG, maybe for a next-gen like Supra2.5-IMG, and we will share our progress and findings on the way to the best open-source T2I model 🤗<br>
|
| 154 |
-
Please give us a like and a follow on Hugging Face if you want to support our work!
|
|
|
|
| 42 |
The model is a tiny diffusion transformer (DiT) with ~105M parameters.
|
| 43 |
|
| 44 |
- Pipeline: text-to-image
|
| 45 |
+
- Parameter Count: 104.1M
|
| 46 |
- Encoder: frozen [Flan-T5-Base](https://huggingface.co/google/flan-t5-base)
|
| 47 |
- VAE: [SD-VAE-FT-MSE](https://huggingface.co/stabilityai/sd-vae-ft-mse)
|
| 48 |
- Image resolution: 256²
|
|
|
|
| 138 |
|
| 139 |

|
| 140 |
|
|
|
|
|
|
|
| 141 |
## Acknowledgments
|
| 142 |
|
| 143 |
- Thank you, FLUX-Reason-6M team, for proving the [LucasFang/FLUX-Reason-6M](https://huggingface.co/datasets/LucasFang/FLUX-Reason-6M) dataset. Without **your** work, this would never be possible!
|
|
|
|
| 149 |
## What's next
|
| 150 |
|
| 151 |
We will keep improving Supra2-IMG, maybe for a next-gen like Supra2.5-IMG, and we will share our progress and findings on the way to the best open-source T2I model 🤗<br>
|
| 152 |
+
Please give us a like and a follow on Hugging Face if you want to support our work!
|