The best vector model is here 🚀
Today, we’re introducing Ideogram's first vector model.
Generate clean, editable SVGs with smooth gradients and sharp typography from a text prompt, or turn any image into a detailed, scalable vector.
Live in Ideogram and the API: ideogram.ai/models/vector
Finally agents that can access all your apps 🚀🚀
I let an AI agent use my iPhone, with no jailbreak and no cable.
A tiny M5StickS3 acts as a Bluetooth mouse and keyboard. The agent sees the screen, decides, and taps. I just talk to it on a call: it opened Clock, searched Safari for the best coffee in San Francisco, and read me the results.
Special thanks to @iamhenryyuan for starting this.
خليت وكيل ذكاء اصطناعي يستخدم جوالي الآيفون، بدون جيلبريك وبدون كيبل.
قطعة صغيرة M5StickS3 تتصرف كماوس وكيبورد عبر البلوتوث. الوكيل يشوف الشاشة، يقرر، ويضغط. وأنا بس أكلمه في مكالمة: فتح الساعة، وبحث في سفاري عن أفضل قهوة في سان فرانسيسكو، وقرأ لي النتائج.
The most precise editing model is here🚀
Ideogram 4.5 is a breakthrough and precise editing.
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.
Marwan retweeted
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.
Marwan retweeted
Ideogram 4.5 is now live on OpenArt ✨
Create from a prompt, then keep refining. Change colors, adjust lighting, or update text, with more consistent details across edits.
Try it now: openart.ai/suite/create-imag…
Marwan retweeted
for those that don't grasp how crazy this is
GPT Image 2.5 Sunburst vs Ideogram 4.5
and by the way it's likely just simple masking/in-painting but it still surprises me it's not the default for the majority of image editing models.
you can tell it's in-painting because you can see the bush around my shoulder slowly turn into a line. it's the same reason my tattoos fade on why side of my arm (the closest to my t-shirt).
no excuse for chopping of half of my head though.
I'm going to have to try a workflow where I use this on every frame of a video.
Marwan retweeted
Holy smoke, Ideogram has a new model version with precise editing, and it’s gonna be open source soon.
Heck yeah. 🔥
Marwan retweeted
Ideogram's new image edit model is insanely good.
To test it, I took this Olipop ad and asked for a series of precise edits - like a creative team exploring variations or localizing content.
Incredible to see how it handles multi-turn changes without warping and artifacts 🤯
Marwan retweeted
Ideogram released Ideogram 4.5 image model for precise editing!
> The model is available on Ideogram and APIs, as well as partner services, and the team is planning to publish open weights of this model soon as well.
> The price ranges from 0.8 to 22 cents per image at native 2K resolution.
Testing time! 👀
Marwan retweeted
ideogram 4.5 is here!!! in my tests it performs better than OpenAI gpt-image-2.5 go try it out!!
Marwan retweeted
We now have Ideogram 4.5 in Gamma!
Congrats to the entire team on the launch! Excited to build more together.
Multi-turn image editing is here. A breakthrough in how AI edits images.
Professionals need to keep refining without losing quality. That’s the problem we set out to solve.
Really proud to be part of the team that built this.
The era of cramming every reference and every change into one prompt is dead.
Multi-turn image editing is here. Keep refining, without losing the details that matter.
This is what we built Ideogram 4.5 for.