Blog

Results for “image generation”

Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.

Get the daily issue

Every new post of the day, in one email. Confirmation required.

All Models LLMs Agents Research AI

#models 215 #agents 151 #llm 135 #research 113 #ai 94 #inference 77 #news 33 #evaluation 32 #benchmark 29 #open-weights 16 #training 16 #automation 14 #deployment 13 #security 13 #optimization 12 #aws 11 #safety 9 #generative-ai 8

LLMsSep 8, 20261 min read

ChatGPT Images 2.5 Released: Improved Instruction Following

OpenAI’s ChatGPT Images 2.5 models now support multi-turn instruction following, faster response times, and better subject preservation in reference images. Two new model IDs, Sunburst and Flare, are available via the API.

From Simon Willison

ModelsSep 8, 20261 min read

ChatGPT Images 2.5: Image Generation from References

ChatGPT Images 2.5 allows for the creation of images based on user-provided ideas, sketches, and reference photos. This update provides more personalized and refined image outputs for engineers deploying image generation models.

From OpenAI news

LLMsSep 5, 20261 min read

Using Blender with coding agents on macOS for image generation

Blender can be used with coding agents on macOS by installing the full application and running prompts via ChatGPT Codex. This enables scene rendering with API-based control.

From Simon Willison

LLMsSep 4, 20261 min read

GPT-6 Astra generates higher-quality SVG pelicans than GPT-5.6 Sol

Astra produces better visual outputs than Sol at similar or lower token costs, with lower input token counts and improved image quality across reasoning levels.

From Simon Willison

ModelsSep 1, 20261 min read

Google AI introduces Google Pics for image creation and editing in Workspace

Google AI announced Google Pics, a tool integrated into Google Workspace for image creation and editing, aimed at simplifying visual content management.

From Google AI blog

Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.

How this blog is made

Every post is a routed request

Each feed entry becomes one request to OpenSmartRoute: the router picks a model with a cost-weighted objective, the editorial-writer skill is layered on the prompt, and the outcome trains the learners - the same pipeline available to every workspace.

Open any post to see which target answered, its confidence, the alternatives and what the request cost. Run the same pipeline yourself: register feeds in the operator console, map a small model under Providers, or call POST /api/v1/route with execute: true.