Ideogram
@ideogram_ai
Think it. Make it. Own it. Research and product company building open frontier models for generative media and design.
0 Following 71.3K Followers
Thank you, Minister @EvanLSolomon, for your time and your energizing remarks. Our team is more excited than ever to build the foundation of generative media in Canada and bring value to our enterprise customers across the globe.
Show more
It was a pleasure hosting Canada's AI Minister @EvanLSolomon at Ideogram's Toronto HQ. We talked about the 3 C's and 2 T's Canadian AI needs: capital, compute, customers, talent, and trust. Proud of our superstar team, building sovereign generative media here at home. 🇨🇦
Show more
P-Image-Ideogram, built with @ideogram_ai, now has a Very High mode.
Very High uses test-time scaling to push final image quality further. Built for hero assets, difficult prompts, and quality-critical generations when people and products have to pop.
• ~5.55s at 1K · $0.033/image (1K) · $0.066/image (2K)
• Five modes from Very Low ($0.003) through Very High
Again, benchmarks agree: This new very high mode is on efficiency-quality based on human and automated evals from @datapointai, @DesignArena, and P-Judger. Full benchmarks results follow in a later post on P-Bench.
Available on @cloudflare @ComfyUI @GammaApp @inference_sh @kittldesign @LeonardoAi @lovart_ai @magnific @picsart @replicate @runware @scenario_gg @togethercompute @wavespeed_ai @wiroai
👉 Free Playground:
🧩 API:
📚 Model page:
Show more
Two new Ideogram models are now on Runware 🎨
@ideogram_ai 4.0q 9.3B, open-weight model:
- Quantized V4.0, running on Runware’s hardware
- Bounding-box layout control for precise text and element placement
- Accepts structured JSON prompting for repeatable output
- Color-palette guidance & multilingual text rendering
- LoRA support for controllable inference
Ideogram Background Remover:
- Pass any image, get back a clean transparent PNG cutout
- Strong edge fidelity for hard boundaries such as typography & logos
Show more
So @ideogram_ai just updated its AI image editor, that allows you to remove objects, change parts of an image, and paint over exactly what you want to edit.
We put it head-to-head against GPT-2 and Nano Banana Pro, and in a lot of our tests, Ideogram actually came out on top.
It’s not perfect, but the level of control you get over exactly what you want to change is incredibly useful.
Show more
Introducing Ideogram Ad Resizer.
Upload one design, choose the placements you need, and export a campaign-ready set for Instagram, Facebook, YouTube, connected TV, display, print, and more - even at extreme aspect ratios.
Available now in the Ideogram app and via the API.
Try it:
Show more
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.
Show more
BREAKING: @PrunaAI continues to be the fastest image model provider on Design Arena.
Built in collaboration with @ideogram_ai, p-image-ideogram frequently generates images in under 3 seconds - establishing a new Pareto frontier for Preference vs. Speed.
No other model at this preference level generates images as quickly.
Congratulations to the teams!
Show more
BREAKING: p-image-ideogram by @PrunaAI and @ideogram_ai establishes new Pareto frontiers for both Preference vs. Price and Preference vs. Speed.
At 1K resolution, the very_low reasoning variant costs just 0.3¢ per image, while low costs 0.75¢ per image. Both generate images in around 3 seconds - roughly 8.6× faster than the Design Arena average.
A major step forward in making high-quality image generation faster and more affordable. Huge congratulations to both teams!
Show more
P-Image-Ideogram is built for production pipelines with four quality modes (Very low, Low, Medium, High), native 1K and 2K generation, and a wide range of aspect ratios.
Latency from 3s to 8s. Pick your point on the speed-quality curve
Show more
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:
Show more
Ideogram Object Remover is now on Runware 🪄
- #1# FID score on the independent OmniEraser benchmark
- Image + mask in, no prompt needed
- Removes objects, shadows, and reflections in one pass
- Multi-region removal in a single request
Show more
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
Show more
The best open-weight image model runs on world-class hardware. Excited to partner with @AMD to deliver Ideogram 4.0 at scale.
Going live with the founders of @ideogram_ai and ComfyUI.
@mo_norouzi (CEO, Ideogram) + @yoland_yan (CEO, ComfyUI ) sit down with @PurzBeats & @hellorob to talk building open-weight text-to-image models, where open weights stand vs. closed APIs, and what's next.
What we'll cover:
→ Founders interview
→ Ideogram 4.0 + open-weight release
→ Structured JSON prompting & bounding box layout control
→ Live community Q&A Drop your questions in chat
we'll put them to the founders live.
Show more
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 👇
Show more
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):
Show more
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?
Show more
Ideogram 4.0 is the #1# open-weight text-to-image model in the world on @DesignArena's third-party leaderboard. We're ahead of every foundation model except closed models from OpenAI and Google.
Frontier quality with open weights, full customization, and data privacy.
Show more
