SupraLabs/Supra2-IMG
text-to-imagetransformersVerified checksumssmallsupraimagefluximgt2i
- License
- apache-2.0
- Size
- 397 MB
- Revision
- main
Mirrored from SupraLabs/Supra2-IMG
All models by SupraLabs →Supra2-IMG
Text-To-Image • 100M Parameters • SOTA quality
Supra2-IMG is a tiny 100M parameters text-to-image (T2I) model that has been trained from scratch on high-quality synthetic data and delivers state-of-the-art image quality for its size.
Samples
Model
About the model
The model is a tiny diffusion transformer (DiT) with ~105M parameters.
- Pipeline: text-to-image
- Parameter Count: 104.1M
- Encoder: frozen Flan-T5-Base
- VAE: SD-VAE-FT-MSE
- Image resolution: 256²
- Latent size: 32²
- Patch: 2
- Context length (Flan-T5): 128 tokens
Model config
D_MODEL: 576DEPTH: 14N_HEADS: 9HEAD_DIM: 64MLP_RATIO: 4.0D_CTX: 768VAE_SCALE: 0.18215
Training
Dataset
The model was trained for 10 epochs on the full LucasFang/FLUX-Reason-6M dataset.
Data preparation
All train data images were downloaded as parquets + metadata and prepared by first chosing the prompt.
This was done in the following order (each next prompt is a fallback for the previous prompt): caption_composition &arrowright; caption_entity &arrowright; caption_text &arrowright; caption_style &arrowright; caption_imaginative.
That way, we ensured only using the highest quality data for pretraining the model.
Exact image count
5.6M images
Epochs count
10 epochs
Hardware
The training ran on a single Nvidia H100 SXM 80GB Runpod Pod for 9 hours (incl. data preparation) with a 2.5TB disk.
How to run the model
First, run:
Then, you can generate images by running:
Recommended settings for sampling
--seed: 0--cfg: 3.0--steps: 50
Expected Output
The script will output something like:
Possible output
Acknowledgments
- Thank you, FLUX-Reason-6M team, for proving the LucasFang/FLUX-Reason-6M dataset. Without your work, this would never be possible!
- Thanks to the creator of HobbyLM-Image for inspiration
- Thanks to Runpod for providing the compute!
- Also a big Thank You To Stability AI and Google for providing SD-VAE and Flan-T5
- Thanks to all the other people inspiring us to make great open-source models for the community!
What's next
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 🤗
Please give us a like and a follow on Hugging Face if you want to support our work!