Image Generation

Today's Stories

1. 1

   Corey Danaher builds AI cities with Midjourney, Adobe, Luma AI

   Corey Danaher, a British futurist and 3D spatial designer, reimagines urban environments with AI-driven architecture, using Midjourney, Adobe, and Luma AI to depict skyscrapers, transit corridors, and megastructures. Blending generative tools with animation and post-production lets a single designer produce cinematic glimpses of possible futures, which points to architectural visuals no longer being limited to traditional rendering pipelines.

   The designs are speculative environments rather than built projects, so their influence hinges on whether architects and planners adopt this AI-and-cinematic approach for real urban renewal work.

2. 2

   AWS shows FLUX.2-klein-4B and Wan2.1-VACE-1.3B on SageMaker AI

   AWS published a code sample deploying a real-time endpoint for FLUX.2-klein-4B image generation and an asynchronous endpoint for Wan2.1-VACE-1.3B video generation from one AWS vLLM-Omni DLC on SageMaker AI. Sharing one container across both models could simplify updates and consistency for teams running generative media, while separate endpoints let each model use the instance type and inference option that fits.

   The numbers AWS reports are single-run checkpoints, not benchmarks, so real throughput and latency will depend on prompts and instance availability. Watch the default 17 frames and 30 diffusion steps, and the note that four steps did not preserve source composition.

3. 3

   Adobe links Gemini and Claude to Photoshop, Acrobat

   Adobe announced in September 2026 it is expanding its connector for Google Gemini and its plugin for Claude, so Photoshop, Lightroom and Adobe Express can be called from Gemini chats and PDFs edited via Acrobat inside Claude. This lets an AI chat act as the entry point for actual production and editing work, rather than only search or text generation, addressing the tool-switching that follows AI generation.

   The value hinges on whether editing inside a chat window is precise enough for real production work; the body offers no user numbers or rollout details beyond the September 2026 announcement.

4. 4

   Comfy Router lets you pick AI generation APIs by price

   Comfy, the developer of the local image and video generation app ComfyUI, released Comfy Router on September 23, 2026, letting users handle several AI generation APIs together. Users can choose among image and video generation APIs by how cheap they are and how loose their limits are, rather than being tied to a single service.

   The headline describes picking by price and limits, but the article body gives no numbers on cost, quotas, or which services are covered yet.

5. 5

   ASICS AI makes on-foot shoe images with no shoot, no model

   ASICS built a generative AI system that creates on-foot styling images of its shoes without a photo shoot or model, and is also using generative AI to explore design variations. In August 2026 it introduced the 3D ShoeSync Viewer at its directly operated store ASICS GRAND FRONT OSAKA, where an AI camera identifies a shoe placed on a fixture and shows its specs, technology, on-foot image and related models at once. Customers can see what a shoe looks like when worn without the time and cost of a shoot or model, and the same AI is being applied to design work, so it appears to touch both storefront sales and product development.

   The value hinges on whether the AI camera correctly identifies products placed on the fixture and whether the generated on-foot images are convincing enough for shoppers. Watch how the viewer performs at ASICS GRAND FRONT OSAKA, its first directly operated store deployment.

6. 6

   Adobe (ADBE) and Broadcom (AVGO) highlighted as AI stock picks

   An undervalued-stock screen highlighted Adobe (ADBE) and Broadcom (AVGO) as AI-driven picks, flagging Adobe's generative AI credit usage as a driver of Average Revenue Per User (ARPU) expansion. As professionals use more generative AI in Adobe's tools, they may hit plan limits and upgrade or buy credit packs, lifting spending per user.

   A single shift in assumptions about how aggressively enterprises pay for deeper Adobe AI usage could reshape its risk and upside, so read the full narrative.