dheeren-tejani/mini-sd

A lightweight, end-to-end implementation of Stable Diffusion built from first principles on a single T4 GPU. Features a custom 192-channel U-Net, VAE, and a CLIP encoder, optimized for consumer hardware and trained on approx. 168k images.

11
/ 100
Experimental
No License No Package No Dependents
Maintenance 10 / 25
Adoption 0 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

TypeScript

License

—

Category

text-to-image-generation

Last pushed

Feb 18, 2026

Commits (30d)

0

GitHub
Text to Image Generation · 50 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/dheeren-tejani/mini-sd"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

filipstrand/mflux

MLX native implementations of state-of-the-art generative image models

86

potamides/DeTikZify

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.

53

FoundationVision/Infinity

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

48

zai-org/CogView

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image...

46

EleutherAI/DALLE-mtf

Open-AI's DALL-E for large scale training in mesh-tensorflow.

42

Explore Transformer Models

All categories Trending Transformer directory Insights