aimagelab/Emuru-autoregressive-text-img
Official PyTorch implementation for "Zero-Shot Styled Text Image Generation, but Make It Autoregressive" (CVPR25)
This project helps graphic designers, marketers, and content creators generate custom text images. By providing a desired text phrase and an example image showcasing a specific font or style, you can produce new images where your text is rendered in that exact style. This is ideal for quickly creating branded visual content or exploring design variations without manual graphic editing.
No commits in the last 6 months.
Use this if you need to generate unique text images with specific stylistic elements from an example, rather than picking from standard fonts.
Not ideal if you only need standard fonts or simple text overlays, or if you prefer manual pixel-level control over generated images.
Stars
24
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jul 31, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/aimagelab/Emuru-autoregressive-text-img"
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
potamides/DeTikZify
Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.
FoundationVision/Infinity
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis
zai-org/CogView
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image...
EleutherAI/DALLE-mtf
Open-AI's DALL-E for large scale training in mesh-tensorflow.