#image-generation
- Ideogram 4.0 Launches as Open-Weight 9.3B Text-to-Image Model with Native 2K Resolution Ideogram image
- Midjourney V8.1 Goes GA with 3× Faster HD Mode and Restored Image Prompts Midjourney image
- Flow-OPD: On-Policy Distillation Pushes GenEval +29 Points on Stable Diffusion 3.5 research
- Qwen-Image-2.0: Unified Image Generation and Editing at 2K Resolution, Top-1 on AI Arena Alibaba research
- Asymmetric Flow Models: SOTA 1.57 FID on ImageNet via Rank-Asymmetric Velocity Parameterization Stanford University research
- Lance: 3B Unified Multimodal Model for Understanding, Generation, and Editing (314 HF upvotes) ByteDance Research research
- Midjourney V8.1 Becomes Default Model: Native 2K Output and 4–5× Speed Boost Midjourney image
- Black Forest Labs Releases FLUX.2 with Multi-Reference Conditioning and 4MP Output Black Forest Labs image
- InterleaveThinker: RL Planner+Critic Pipeline for Interleaved Text-and-Image Generation CUHK Multimedia Lab research
- Midjourney V8.1 Becomes Platform Default, Replaces V7 with 2K Native Resolution Midjourney image
- OpenAI Retires DALL-E 2 and DALL-E 3 APIs on May 12 OpenAI image
- OpenAI DALL-E 2 and DALL-E 3 APIs Shut Down on May 12 OpenAI image
- Yandex Improves Alice AI ART: Russian Text in Generated Images 3x More Accurate Yandex image
- InterleaveThinker: RL Framework for Agentic Text-and-Image Interleaved Generation research
- Sber unveils Kandinsky 6.0 Image — flagship image generation model Sber image
- Midjourney Launches Draft Mode for V8.1 with 24-Image Exploration Grid Midjourney image
- Sber Launches Giga-Art AI Art Festival Using Kandinsky 6.0 Sber industry