SupraLabs/Supra2-IMG
text-to-image model by SupraLabs
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. The model is a tiny diffusion transformer (DiT) with 105M parameters. The model was trained for 10 epochs on the full LucasFang/FLUX-Reason-6M dataset. 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): captioncomposition → captionentity → captiontext → captionstyle → captionimaginative. That way, we ensured only using the highest quality data for pretraining the model. 5.6M images 10 epochs The training ran on a single Nvidia H100…
Read the full model card ↗ · Preview checked 2026-11-03T23:32:26.395Z
Inside the original model card — Document outline
- Samples
- Model
- About the model
- Model config
- Training
- Dataset
- Data preparation
- Exact image count
- Epochs count
- Hardware
- Benchmarks
- How to run the model
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
SupraLabs/Supra2-IMG is a text-to-image model repository published by SupraLabs on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-image
- Library
- transformers
- Recent downloads (30 days)
- 784
- Cumulative likes
- 170
- Hugging Face trending score
- 50
- Reported safetensors parameters
- Not reported
- Architecture
- SupraDiT
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-21T14:05:35.000Z
- Last modified
- 2026-09-30T13:24:10.000Z
Compatibility and lineage
Reported languages: en
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-02T06:38:30.819Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
stabilityai/stable-diffusion-xl-base-1.0
abenzerps/Qwen-Image-2.1-Uncensored-Quantized