I broke 11 images on purpose (extra hands, a third leg, the same person twice, seven fingers, too many sunglasses and lots of typos) and gave them to 7 AI image editors to fix: Krea 3, GPT Image 2.5, Nano Banana 2, Seedream 5, Flux 3, @grok Imagine and @ideogram_ai 4.5. Same image, same prompt, one try each. Do you agree with the tier list? Which image editor are you using, and what should I test next? Tell me in the comments. TIER LIST: SS Ideogram 4.5 | S GPT Image 2.5, Grok Imagine | A Flux 3 | B Krea 3, Seedream 5 | C Nano Banana 2

Ideogram 4.5 is amazing at image editing. This model lets you make adjustments to images without sacrificing quality. Whether it's text editing, removing or adding new features or changing the entire scene, Ideogram does a fantastic job for you. Quick tutorial:

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models, so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? @ideogram_ai's Ideogram 4.5 and @bfl_ml's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.

You can use Ideogram 4.5 to transform famous paintings into photos using this one prompt: "Turn this painting into a realistic scene." 1/ The Scream, Edvard Munch, 1893 🧵

I spent thousands of hours photographing and editing as a hobby. It brought out my creativity and attention to detail. With so much code in my head, I want to return to photography to relax. But I have hundreds of unedited photos because I can't justify the editing time. Really hope Ideogram works as advertised. Open weights are coming, and I'm looking forward to hopefully running it locally to EDIT my photos, not GENERATE them.