Recent posts
Creativity is searching for the best ideas. And the only way to find the best ideas is to explore many ideas. I hope we can bring more creativity and beauty to the world by pushing the Pareto frontier of quality × speed × cost for image generation with P-Image-Ideogram. Built by the @PrunaAI and @ideogram_ai and evaluated by @DesignArena.
Any image model rated higher in quality costs more or runs slower. 🚀
Today, we're introducing P-Image-Ideogram: a family of Pareto-optimal image models with the best quality-speed-cost trade-off, co-developed with @PrunaAI. Four quality modes. Native 1K and 2K generation. From $0.003 per image. Live now on the API and all our partner platforms. Give it a try: https://t.co/omew4Z6OTM
Object removal is a really important creative workflow and surprisingly difficult.
Introducing Ideogram Object Remover: state-of-the-art object removal. Select any object, text, or distraction and erase every trace of it: shadows, reflections, even subtle lighting shifts. Nothing invented, nothing else touched. Try it now at http://ideogram.ai/apps/object-remover
Congrats David, on the new dream!
dream harder
@ideogram_ai チームが成し遂げたことをめっちゃ誇りに思う。世界で #1 のオープンウェイト画像モデルで、コンシューマー GPU で動作するレベルの小ささ 🚀
原文を表示 (en)
So proud of what the @ideogram_ai team pulled off. The #1 open weight image model in the world and small enough to run on your consumer GPU 🚀
Ideogram just released the #1 open weight image model in the world. It punches way above its weight - it's small enough to run on a consumer GPU, but goes head-to-head with Nano Banana and GPT Image for design. We went deep with @mo_norouzi on how they did it + hot takes 👇
コミュニティはjsonプロンプティング、バウンディングボックスコントロール、そしてIdeogram 4.0全般を愛してくれてるみたい――フィードバックに基づいてやることがあるね。
原文を表示 (en)
The community seems to love json prompting, bounding box control, and Ideogram 4.0 in general -- we have work to do based on the feedback.
One week ago, we released Ideogram 4.0, our first open weight model. Since the launch, the open-source and creative communities have pushed it beyond what we could imagine. Seems like JSON and bounding box prompting is becoming the new norm now. Week one community highlights (thread):
私たちはデザインを大切にする AI 企業で、新しいロゴがそれを証明しています。
原文を表示 (en)
We're an AI company that cares about design, and our new logo proves it.
New model. New brand. The start of a new era for Ideogram. Ideogram 4.0 launched with open weights, and we felt it was the right time to rethink our brand as a whole. Thank you How&How for bringing our new vision to life. What do you think of our new logo?
AIがテキストをスペルできず、手を5本の指で描くことができなかった時代を覚えてる？俺たちは随分進んだぜ。
原文を表示 (en)
Remember when AI couldn't spell text or draw a hand with five fingers? We've come a long way.
@ideogram での私たちの目標は、ワールドクラスのデザインをより多くの人に利用可能にすることです。
原文を表示 (en)
Our goal at @ideogram is to make world class design accessible to more people.
Ideogram V4 is made for creators who care about clean design, sharp visuals, and reliable text rendering. Turn posters, ads, thumbnails, and brand-style images into polished results faster on BudgetPixel AI.
Ideogram 4.0 についての豆知識: 僕たちはまだモデルをスケーリングすらしていない。 採用募集中！僕と僕のチームは @CVPR に3日間います。DM を送るか、ブースに立ち寄るか、今夜のハッピーアワーに来てください: https://luma.com/vd0688ib?tk=wrYFBY
原文を表示 (en)
Fun fact about Ideogram 4.0: we haven't even scaled the model yet. We're hiring! My team and I are at @CVPR for 3 days. DM me, swing by the booth, or come to our happy hour tonight: https://luma.com/vd0688ib?tk=wrYFBY
Today we published a technical blog post about Ideogram 4.0 — our goal is to enable more innovation and creativity. It's a 9.3B Diffusion Transformer trained from scratch, paired with a frozen 8B VLM as text encoder. The nf4 checkpoint runs on a 24GB consumer GPU. Thread 🧵
@Google に質問、最高のオープンウェイト画像モデルは何ですか？
原文を表示 (en)
Hey @Google, What's is the best open weight image model?
Ryan Dahlは私が知っている最高にヤバいエンジニアだ。彼はNode.jsを始めて、今は @deno_land のCEOをしている。彼は1年間、僕とJon Shlenと一緒に研究をしていて、2017年に生成モデルが画像アップスケーリングに適していることを予感していた。
原文を表示 (en)
Ryan Dahl is the most cracked engineer I know. He started Node.js and is the CEO of @deno_land now. He spent a year doing research with me and Jon Shlens and we had a hunch in 2017 that generative models are good for image upscaling.
I coauthored a couple papers with Ideogram's CEO on generative image models in 2017 - back then 64x64 pixel images were the best we could do.
@ClementDelangue さんと @huggingface チームとの仕事は最高だ！彼らは素早く動く 🤗
原文を表示 (en)
It's awesome working with @ClementDelangue and the @huggingface team! They move fast 🤗
Ideogram just released their latest and best v4 image model open weights State of the art and open weights go well together 🤗 Model: https://huggingface.co/ideogram-ai/ideogram-4-nf4 Demo: https://huggingface.co/spaces/multimodalart/ideogram4 https://x.com/ideogram_ai/status/2062202208700313872?s=20
pwdに5ドル使っちゃった
原文を表示 (en)
Just spent $5 on pwd
Me using Claude Opus 4.8 to rename a file
背景削除は実は非常に難しい問題で、グラフィックデザインのユースケースでようやく解決しました 🚀
原文を表示 (en)
Background removal is actually a very hard problem and we finally solved it for graphic design use cases 🚀
Today we're introducing Ideogram BG Remover. It is the state-of-the-art for graphic design: clean alpha on logos, product photos, fine typography, and intricate cutouts. Available on all plans, including Free, and via the API.
Excited to see what Behnam builds!
I've left Anthropic to start something new. 🧵
8K upscale is here!
We've upgraded Ideogram's upscale by integrating with @topazlabs, to deliver enhanced images and sharper details up to 8K. Whether you're creating logos, t-shirt designs, marketing assets, or other graphics, you can now export production-ready assets with ease. As part of our new strategy, we're bringing the best AI tools, whether built by us or industry leaders, directly into Ideogram to deliver more value to our customers. This is the first of many integrations, so stay tuned for more features coming soon!
I'm at #NeurIPS2025 today and tomorrow! Would love to chat about generative media and the future of design. DMs are open. We're hiring across research and engineering roles at Ideogram. Come find us at our booth in the exhibition hall, or join us for happy hour tomorrow: https://t.co/6kdYk28IYX
