Topic
Image-generation — AI news & analysis
AI-generated content. Everything on this page was written by an automated AI editorial system and published without prior human review. How this works ›
Every Pick Right story tagged image-generation — 6 articles, newest first. All news →
ByteDance's Seedream 5.0 Pro: the AI image model that outputs editable layers and renders text in 15 languages
ByteDance's Seed team shipped Seedream 5.0 Pro on July 8 — a professional-tier image model with two features that actually matter for production work: it can split a single render into 10+ transparent-PNG layers (auto-filling what the subject was hiding, so you edit in Figma or Photoshop without masking), and it renders legible text in 14–15 languages, the hardest problem in image generation. Here's what it does, where it fits against Nano Banana Pro and Midjourney, and the ByteDance caveats a commercial buyer should weigh.
Read story →FLUX 3 generates image, video, and audio from one model — Black Forest Labs' bet on natively multimodal generation
Black Forest Labs unveiled FLUX 3 on July 23 — what it calls the first natively multimodal architecture, generating image, video, and audio from a single set of jointly-trained weights. FLUX 3 Video makes 20-second clips with synchronized native audio (dialogue, sound effects, ambient), and in the company's own evals human reviewers preferred it over Runway Gen-4.5 (77%) and Luma Ray 3.2 (93%). Video and a robotics-focused Action model are in early access now; image generation and open weights come later. Here's what actually ships today and how it stacks up.
Read story →Midjourney finally ships video — and it's roughly 25× cheaper than Sora was
Midjourney V1 Video animates Midjourney images into 5-second motion clips at roughly the cost of upscaling — about 25× cheaper than Runway, Veo 3, or the late Sora. No native audio, but the artistic style transfers from the still image. For artists already on Midjourney, this changes the AI video calculation.
Read story →DALL-E 3 shuts down in 20 days — here's the migration plan
OpenAI is deprecating DALL-E 2 and DALL-E 3 on May 12, 2026 — three weeks from today. GPT Image 1.5 is the replacement; GPT Image 2 is expected to launch before or shortly after the cutover. Migration steps, cost comparison, and alternatives outside OpenAI.
Read story →OpenAI's big week: ChatGPT Images 2.0, Codex Enterprise, Chronicle
OpenAI shipped three consequential products in 48 hours — ChatGPT Images 2.0 with 'thinking'-enabled generation, Codex Labs and GSI enterprise partnerships, and Chronicle on-device screen memory for Mac Pro users. Here's what matters and what's hype.
Read story →Nano Banana now makes images from your Google Photos
Google rolled out personalized image generation in Gemini this week — Nano Banana can now create images using your private Google Photos as reference material. 'A claymation of me and my family on our favorite hike' works out of the box. Paid subscribers only, US first, opt-in required.
Read story →