Speechmatics - API for Voice AI Agents
Mini toolsT2I L2P
By Tencent
L2P, short for Unlocking Latent Potential for Pixel Generation, is an open-source Tencent Youtu Research project for efficient text-to-image pixel-space diffusion. It provides a transfer paradigm that converts latent-space diffusion weights into a pixel-space initialization, then fine-tunes and merges the trained delta back for inference. The released setup includes 1K-resolution training code, inference code, weights, and dataset support, with the listed L2P-z-image checkpoint using a 6B model built around Z-Image-Turbo. The project targets high-quality end-to-end pixel-space generation with lower compute and data requirements than training pixel models from scratch.
New
Multimodal
Gen 3
Overview
T2I-L2P is Tencent Youtu Research’s open-source pixel-space diffusion transfer method for turning latent text-to-image models into high-quality pixel-generation models.
About Tencent
Tencent is a world-leading internet and technology company that develops innovative products and services to improve the quality of life of people around the world.
Industry:
Technology, Information and Media
Company Size:
110558
Location:
Shenzhen, CN
Website:
tencent.com
Tools using T2I L2P
No tools found for this model yet.
Last updated: May 22, 2026
