NEWS

Hey city adventurers!🌍 Guess what just popped up in the downtown skyline? A GIANT, squishy fur baby that’s turning the city into its own playground—using bridges as naps spots and skyscrapers as scratch posts, and making strangers stop to gush! 🐾🤯 Wanna bring this whimsical “giant pet takes over the city” vibe to life? Create… Read more

Perface In recent years, powerful Diffusion Models have taken the field of AI image editing by storm, enabling the generation of stunning and photorealistic images. However, two major pain points lurk behind this achievement: uncontrollable effects and low efficiency. Due to their generation mechanism where “a single change affects the whole”, even when only a… Read more

Are you ready to witness the next evolution in video generation? Forget all your inherent perceptions about AI-created content. We’re talking about long-form videos that don’t just look good—they tell a story with stunning detail and perfect coherence. As AI video generation enters the “content industrialization” stage, the self-developed multimodal large model by HiDream.ai now supports high-consistency… Read more

1.Payment-related 1.1Subscription and Payment Question: Unable to complete payment for membership purchase Answer: You can try several times, such as refreshing the page or restarting the website. If the issue persists, please feel free to contact us via email. This might be a temporary technical issue, and our team will do their best to resolve… Read more

Following its topping of the open-source image generation model arena list, HiDream.ai has achieved another milestone! Its latest open-source model, HiDream E1.1, has successfully entered the first tier of the Artificial Analysis list for image editing agents. As a leading open-source image editing model, it comprehensively outperforms mainstream models such as Flux.1 Kontext, continuously refreshing… Read more

When it comes to AI-generated video, clarity and fidelity have always been tough nuts to crack. Now, a team from HiDream.ai has hit a major milestone: their GenVE (Generative Video Enhancement) framework has been officially accepted for presentation at ICCV 2025. Research Background and Motivation How GenVE Works Semantic Alignment When high-quality reference images of… Read more

In recent years, autoregressive models, as the cornerstone of large language models (LLMs), have achieved remarkable success in the field of text generation. However, when applied to image generation, they often suffer from poor detail performance in generated images and much slower-than-expected inference speed due to their inherent one-way prediction mechanism and reliance on discretized… Read more