Jonathan Ho

Introducing Ideogram Character -- the first character consistency model that works with just one reference image. Now available to all users for free! Create consistent character images in any style, expression, scene, and lighting. Who wants video next? 🥺

@kvfrans nice

Stare at policy improvement and diffusion guidance, and you may notice a suspicious similarity... We lay out an equivalence between the two, formalizing a simple technique (CFGRL) to improve performance across-the-board when training diffusion policies. arxiv.org/abs/2505.23458

Today, we're releasing a major upgrade to Ideogram 3.0: enhanced realism, more versatile styles, improved prompt following, and greater diversity. You can now use Magic Fill and Extend with 3.0 in Ideogram Canvas to edit both uploaded and generated images. Ideogram 3.0 is finally available on our API at developer.ideogram.ai

Meet Ideogram 3.0 — stunning realism, creative designs, and consistent styles, all in one powerful model. And it's blazingly fast. Now available to all Ideogram users for free.

Today, we’re introducing Ideogram Canvas, an infinite creative board for organizing, generating, editing, and combining images. Bring your face or brand visuals to Ideogram Canvas and use industry-leading Magic Fill and Extend to blend them with creative, AI-generated content.

Join us at Ideogram to build the future of AI for creativity. We have the best ML and engineering team in the world in generative media. DM me with the most impressive work that you've done so far, or apply directly at jobs.ideogram.ai

@pabbeel @ideogram_ai Thank you @pabbeel! Your impact of your mentorship extends way beyond the PhD

Amazing work by @ideogram_ai team. 80/20 rule, but in reverse: this team is willing (and exceptionally capable!) to put the extra 80% ingenuity and effort to nail that last 20% so you get what you really want! And proud PhD advisor moment for myself, congratulations @hojonathanho!!!

Introducing Ideogram 2.0 — our most advanced text-to-image model, now available to all users for free. Today’s milestone launch also includes the release of the Ideogram iOS app, the beta version of the Ideogram API, and Ideogram Search. Here’s what’s new… 🧵

Introducing Ideogram 1.0: the most advanced text-to-image model, now available on ideogram.ai! This offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting.

We're hiring a machine learning engineer excited about pushing the frontier of AI for creativity. You'll work directly with the the pioneers of denoising diffusion models. You can apply here if you're interested: jobs.ashbyhq.com/ideogram/557ee…

Today, we’re opening Ideogram to everyone on the planet! Sign up at ideogram.ai and have fun! Ideogram enables you to turn your creative ideas into delightful images, in a matter of seconds. It’s free and has no limits, and it can render text! ideogram.ai/publicly-avail…

We love our growing community ♥️ and we're committed to making ideogram.ai safe for everyone on the planet to experience it! Please join our new discord server discord.gg/ideogram so we can talk! #ideogram

diffusion models

Excited to share our work "On distillation of guided diffusion models"! Our distillation approach allows classifier-free guided diffusion models to generate high-quality samples using as few as 1-4 sampling steps😮

Two important breakthroughs from @GoogleAI this week - Imagen Video, a new text-conditioned video diffusion model that generates 1280x768 24fps HD video. And Phenaki, a model which generates long coherent videos for a sequence of text prompts. imagen.research.google/video/

Imagen Video is on arXiv: arxiv.org/abs/2210.02303

Also, check out Phenaki, a complementary approach from Google Research for text to video that generates long coherent videos for a sequence of text prompts: phenaki.github.io We are looking forward to combining the strengths of Phenaki and Imagen Video!

Excited to announce Imagen Video, our new text-conditioned video diffusion model that generates 1280x768 24fps HD videos! #ImagenVideo imagen.research.google/video/ Work w/ @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans

“Imagen Video” let’s you type in words and generate videos. How does it work? A quick thread on the work by @hojonathanho @wchan212 @Chitwan_Saharia @jaywhang_ @RuiqiGao @agritsenko @dpkingma @poolio @mo_norouzi @fleet_dj @TimSalimans: 👇