AI Images

The prompts are worth more than the verdict.

Recraft put seven briefs through its own V4.1 and through Ideogram V4, then told us which one won. A company marking its own exam is not evidence. The seven briefs, printed in full, are a different matter entirely.

The prompt stopped being text.

Google switched off three Imagen 4 endpoints today. What replaces them has no separate image call at all: pictures now come out of the same request as words, and that request will accept fourteen reference images, a video, or a link to one.

The braces were never the point.

Everyone is writing image prompts as neat objects now, and the pictures do look better. The reason is not the one being shared, and knowing the real one makes the tidiness optional.

Five briefs, written out.

The five image jobs people are most often asked to produce, each written as a complete brief you can paste today, with the lines that must not move held apart from the lines left open.

Five prompts, written as objects.

A macro portrait, a product, an interior, a second shot of the same character, and a short clip. Each one complete, each one with the single line to change first.

AI Prompting in JSON.

Take one prompt you already use and write it out as an object. Three fields, one entry per thing in the picture, and a position only where the position is the point.

Four ways to shape a prompt.

Plain sentences, comma tags, blocks you keep constant, and JSON. Ideogram 4.0 reads JSON natively, and its own guide tells you when to stop using it.

Shipped, or merely announced.

Four releases in seven days. The question worth asking is not which is most impressive. It is which one you can put to work this afternoon, and the answers are further apart than the headlines suggest.

When your taste should speak.

Midjourney V8.2 landed on July 24 with a personalization system that reads your rating history more closely. That makes your own taste a louder ingredient in every render, and it makes knowing when to quiet it part of the craft.

The ten-second review: judging AI images at named points

Luxe 118 — Draft fast, then commit (Nano Banana in Search)

Google is bringing from-scratch image creation into Search, powered by its fast, low-cost Nano Banana tier. For creators, that tier is a draft engine.

AI Muse Image Generation

Meta's first in-house image model plans, gathers references, and checks its own work before it answers. The video half is a preview, not yet a tool.

AI Designs & Prompts - the last five percent.

Recraft Studio can now edit the vector it just made. Pull a point, recolor one shape, duplicate a letterform.