Zero-shot image-to-text generation with BLIP-2

Welcome aMUSEd: Efficient Text-to-Image Generation

Introducing ChatGPT Images 2.0

ChatGPT Images 2. 0 introduces a state-of-the-art image generation model with improved text rendering, multilingual support, and advanced visual reasoning.

Introducing 4o Image Generation

At OpenAI, we have long believed image generation should be a primary capability of our language models. That’s why we’ve built our most advanced image generator yet into GPT‑4o.

Open Preference Dataset for Text-to-Image Generation by the 🤗 Community

BLM-SGAN: Bidirectional Language Modeling for Semantic-Spatial Text-to-Image Generation

arXiv:2606. 08847v1 Announce Type: cross Abstract: Despite the success of image generation from text descriptions, it still faces challenges that are difficult to overcome in domains such as natural language processing (NLP) and computer vision (CV).

Training Design for Text-to-Image Models: Lessons from Ablations

Hierarchical text-conditional image generation with CLIP latents

Nexus: Structured Synergy for Efficient Text-to-Image Generation using Rectified Flow Model

Diffusion and flow matching models have made significant progress in text-to-image generation, yet high computation, quadratic complexity, and large memory footprint hinder high-resolution synthesis and edge deployment. We propose Nexus, which integrates sparse architecture, linear complexity, and low-bit quantization.

PRX Part 3 — Training a Text-to-Image Model in 24h!

Assisted Generation: a new direction toward low-latency text generation

How far can we go with ImageNet for Text-to-Image generation?

The paper argues that large-scale text‑to‑image models can be trained effectively on ImageNet, provided the dataset is enriched with carefully crafted text and image augmentations. Using this approach, the authors match the performance of state‑of‑the‑art models such as FLUX, surpassing SD3 on GenEval by +5 points and SDXL on DPGBench by +12, while employing only 1/1000th of the training images and significantly fewer parameters. The method requires just 500 hours of H100 GPU time, making it a more reproducible and accessible alternative to massive web‑scraped datasets.

AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization

AdaPilot introduces a scene-adaptive, cross-generator policy for optimizing text-to-image generation quality. By framing multi-turn image generation as a Markov Decision Process and using reinforcement learning, it decouples the policy from specific generator internals, incorporates scene-aware and process-level rewards, and achieves superior quality and generalization compared to baselines. Experiments demonstrate that a single AdaPilot policy can transfer zero‑shot to unseen generators while consistently improving performance across all evaluated models.