Image created with gemini-3.1-flash-image-preview with claude-opus-4.7. Image prompt: Byzantine gold-ground mosaic icon of a flattened frontal saint holding a small hammered-gold painted panel that emits an outward spiral gyre of loose tesserae into the gilded field, brushes fanned like a halo of rays in the saint’s other hand, circuit-ring halo, deep imperial purple and Tyrian crimson robes with Aegean blue trim, warm candlelit directional glow, visible grout and tactile tesserae grain, symmetrical centered composition with generous negative space, bold ivory Trajan-capital title ‘IMAGES’ across the lower third, 16:9 full-bleed, painterly reverent illuminated-manuscript feel.
Nano Banana 2 (Gemini 3.1 Flash Image) and Nano Banana Pro (Gemini 3 Pro Image) are now GA. – Flash: $0.045/image. – Pro: $0.134/image. 🆕 Nano Banana 2 (Flash) support video as input, analyzes footage and generate context-aware images, thumbnails, and infographics from it.
https://x.com/_philschmid/status/2060064810633482580
Tencent dropped Z-Image 6B with pixel space gen. – no VAE – 1k resolution – high efficiency It’s a transfer learning framework that turns any regular Flux/SD model into a full pixel-space beast
https://x.com/wildmindai/status/2057797994242523317
Today we’re releasing 1-bit and Ternary Bonsai Image 4B. A new family of image-generation models designed to run high-quality diffusion inference on local hardware: from laptops to phones.
https://x.com/PrismML/status/2059339157600969199
Improving AI labels for viewers and creators – YouTube Blog
https://blog.youtube/news-and-events/improving-ai-labels-viewers-creators/
MAI-Image-2.5 launches at No. 3 on Arena | Microsoft AI
https://microsoft.ai/news/mai-image-2-5-launches-at-no-3-on-arena-ai/
Meet MAI-Image-2.5 – ranked third on the @arena text-to-image leaderboard. It’s another great advance in quality. And with Build just a week away, there is much more to come. Learn more here:
https://x.com/MicrosoftAI/status/2059344061358563838
Meet MAI-Image-2.5 – ranked third on the @arena text-to-image leaderboard. It’s another great advance in quality. And with Build just a week away, there’s much more to come from the @MicrosoftAI team. I can’t wait.
https://x.com/mustafasuleyman/status/2059346031167570299
PIXLRelight: Controllable Relighting via Intrinsic Conditioning”” TL;DR: physically grounded feed-forward relighting framework combining PBR conditioning and transformer rendering for controllable single-image illumination editing
https://x.com/Almorgand/status/2059759763546620149
Leave a Reply