GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors
Paper โข 2609.02349 โข Published
How to use innerway/GlyphAnchor with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("innerway/GlyphAnchor", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Official checkpoints for GlyphAnchor, a method for improving visual text rendering in text-to-image generation and image editing.
| Model | Task | Base model |
|---|---|---|
GlyphAnchor-Z-Image |
Text-to-image generation | Z-Image |
GlyphAnchor-FireRed-Image-Edit-1.1 |
Image editing | FireRed-Image-Edit-1.1 |
GlyphAnchor-Qwen-Image-Edit-2511 |
Image editing | Qwen-Image-Edit-2511 |
Please refer to our GitHub repository for installation instructions, inference code, and examples.
@inproceedings{xiang2026glyphanchor,
title={GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors},
author={Qiang Xiang and Shuang Sun and Binglei Li and Yibo Chen and Xu Tang and Yao Hu and Junping Zhang},
booktitle={The Fortieth Annual Conference on Neural Information Processing Systems},
year={2026},
url={https://openreview.net/forum?id=c3aMyawBN4}
}