New top open source AI image model:
HiDream-O1-Image
It's prompt adherence and world understanding edges pretty close to GPT Image 2, especially for text & infographics.
https://t.co/K5WGn2uxe5
Open source is winning. 🔥
We just hit #1 on the @ArtificialAnlys Image Arena for open-weights Text-to-Image models! HiDream-O1-Image-Dev-2604 is officially going toe-to-toe with top proprietary models like FLUX.2 [max].
HiDream-O1-Image-Dev-2604 debuts as the leading open weights Text to Image model in the Artificial Analysis Image Arena, with the base HiDream-O1-Image and HiDream-O1-Image-Dev also available open weights but landing lower on the leaderboard
@HiDream_AI's O1-Image family spans three models: the 8B HiDream-O1-Image, its distilled HiDream-O1-Image-Dev, and HiDream-O1-Image-Dev-2604, a fine-tune of Dev with a prompt-enhancement pipeline, previously listed pseudonymously as Peanut. The base and Dev models accept text plus up to 10 image inputs, spanning generation and instruction-based image editing.
On the Artificial Analysis Text to Image Arena, HiDream-O1-Image-Dev-2604 leads all open weights models, delivering quality similar to proprietary models like ByteDance's Seedream 4.0 and Black Forest Labs' FLUX.2 [max]. In Image Editing, HiDream-O1-Image is the second-highest open weights model, behind only Tencent's HunyuanImage 3.0 Instruct.
Weights and the full inference pipeline (including HiDream's prompt refiner used during evaluation for HiDream-O1-Image-Dev-2604) are open-source on Hugging Face and GitHub under the MIT license.
HiDream-O1-Image and HiDream-O1-Image-Dev are also available across third-party API providers including Fal, priced on Fal at $10/1k images and $5/1k images respectively.
Congratulations to @HiDream_ai on the releases!
See below for comparisons between the HiDream-O1-Image family and other leading models in the Artificial Analysis Image Arena 🧵
🎉https://t.co/dhYCSjNcAL Completes a New Round of Financing, Fully Committed to Developing Next-Generation Native Omnimodal World Models!
💻More information👉https://t.co/ZbRxrueaGk
🚀 Official Launch! https://t.co/dhYCSjNcAL officially unveils ZhenZan AI(https://t.co/zftU0et7Br), the world’s first professional-grade AI Film & TV creation and collaboration agent!
🔓The new era of creation starts now!
🤖 【CTO’s Take 3】The Agentic future
Agentic App = Harness × Skills, running on an OS. 🧩
The endgame isn’t a better video generator. It’s a creative agent — a system that actually completes tasks end-to-end. ✅
🚀【CTO’s Take 1】Startups win by going deep, not broad. General-purpose models = Big Tech’s battlefield. Vertical focus is the only path.
🔄 【CTO’s Take 2】Multimodal is yesterday. The future is omni-model. Unified tokenization across all modalities = arbitrary input+output.
Dr. Ting Yao, Co-founder & CTO of https://t.co/dhYCSjNcAL,
On the endgame of world models +The AI video space is rapidly reshaped.⚡
At this moment, he shares his take.💡
His vision is half a step ahead. 🎯
Next 2 days: Deep dives into our CTO's latest thoughts!🧠
🚀 https://t.co/dhYCSjNcAL x Noitom Robotics
We’re excited to announce a strategic partnership to build a new paradigm for Embodied AI data! By fusing real-world motion capture with generative video, we’re scaling high-quality training data to 10,000+ hours this year.
🚀 HiDreamClaw: The "Vertical Era" is HERE!
General AI chats; we CREATE. 🎨🎥
Your ultimate creative partner is LIVE on vivago web.
Start building! 🔗https://t.co/iZtWHqpxFv
#HiDreamClaw#AIAgent#vivago#AI#HiDreamAI
Challenge: Use vivago to give your photo a cultural makeover in 30 seconds. 🎁
Choose from Egyptian, Indian, or Indonesian templates, upload photo, and watch the transformation.@vivago
👉Click to try vivago regional style templates
#HiDreamAI#vivago#AIChallenge#CulturalFusion
Vivago transforms your cute pet flight ideas into charming digital art. What's your must-make creation?
Vivago tutorial: craft perfect pet plane scenes—cat-shaped aircraft, baby captain & more.
Drop 🐱🐶✈️ in the comments!
#HiDreamAI#AI#CreativeAI#vivago
Forecast: Your New Year's “Fortune” is out for delivery by stallion. Clear skies. On schedule. @vivago_ai
https://t.co/dhYCSjMELd wishes you joy that arrives “immediately”!
#YearOfTheHorse#GoodFortune#HiDreamAI
🚀 Vivago (China Edition) upgrade + FREE access!
✨ Visual redesign | 🤖 Self-developed AI (Eastern aesthetics) | 🐾 Dancing pets | 🎬 Custom AI videos
🎁 Feb 16 - Feb 23: ALL templates & AI effects FREE! No catch. 🧧
Try it now 👉https://t.co/56ME3dACSN
#vivago#SpringFestival
Challenge: Use vivago to create something special for them in 30 seconds. 🎁
Select the "Valentine's Template", upload a photo, and witness the magic.🪄
👉Click to try vivago Valentine’s templates @vivago_ai#vivago#AIChallenge#Valentines#TryItNow
QUICK CHALLENGE: If the framed artwork next to you could do ONE thing, what would it be?🖼️
Blink? Breathe? Bloom?
Tell us. Then tap our link to actually make it happen. It's easier than you think.@vivago_ai#HiDreamAI#ArtPrompt#AIChallenge#vivago
Step 3 of AI Comic: Stop stacking single images. Start building the storyboard. 🔥
This framework turns your static frames into a breathing narrative—the key to making your work readable, not just viewable.@vivago_ai#AI#Storyboard#AIArt#AITools#vivago#DigitalStorytelling