Deci AI Launches DeciDiffusion 1.0, an 820 Million Parameter Text-to-Image Generation Model

3DV-TON: Revolutionary Video Try-on with Diffusion Model Driven Texture 3D Consistency

3DV-TON (Textured 3D-Guided Consistent Video Try-on via Diffusion Models) is an innovative technology that delivers a realistic video try-on experience with texture 3D guidance using diffusion models. According to AIbase, 3DV-TON leverages advanced 3D geometry and texture modeling combined with video diffusion models to ensure consistency and realism of clothing in dynamic videos, offering significant potential for e-commerce, fashion, and virtual reality applications.

Jimeng AI 3.0 Global Launch: Cinematic Visuals and Precise English Typography Lead the Way in AI Creation

ByteDance's Jimeng AI has officially launched Jimeng AI 3.0 globally, marking a significant expansion of its text-to-image and video generation technology into international markets. According to AIbase, the new version boasts cinematic image quality, 2K resolution output, hyperrealistic textures, and precise English typography, particularly excelling in English text generation and font control, surpassing the performance of the previous Chinese version. The launch announcement has generated significant buzz on social media platforms. Features can be experienced via the Jimeng AI website and mobile application.

Ostris Releases Flex.2-preview, an 800M Parameter Diffusion Model Revolutionizing ComfyUI Workflows

The Ostris team has released Flex.2-preview, an 800 million parameter text-to-image diffusion model designed for integration into ComfyUI workflows. According to AIbase, this model excels at generating images with strong control over lines, poses, and depth. It supports general control and inpainting functionality, continuing the fine-tuning evolutionary path from Flux.1Schnell to OpenFlux.1 and Flex.1-alpha. Flex.2-preview is available on Hu...

Sand AI Open-Sources MAGI-1 Video Generation Model: Infinite Scalability, High Fidelity

On April 21, 2025, Sand AI open-sourced its video generation model, MAGI-1. With its innovative autoregressive diffusion architecture and exceptional performance, it quickly became a focal point in the generative AI field. Licensed under Apache 2.0, the code, weights, and inference tools are available on GitHub and Hugging Face, providing a powerful creative tool for global developers. MAGI-1 is based on a diffusion transformer architecture, incorporating block causal attention and parallel attention.

New Framework d1 Advances Diffusion Model Inference, Sparking a New Wave of Reinforcement Learning Applications

AMD GPU Performance Leap! Significant Stable Diffusion Model Optimization

AMD's advancements in AI are noteworthy, particularly its latest optimizations for the Stable Diffusion model. Recently, Stability AI released an ONNX-optimized version of Stable Diffusion, resulting in significantly improved performance for AMD Radeon GPUs and Ryzen integrated graphics in AI tasks, with speed increases up to 3.8 times faster. This progress narrows the gap with NVIDIA's ecosystem...

Doubao's Deep Thinking and Text-to-Image 3.0 Models Officially Open APIs to Enterprise Clients

Doubao recently released a series of updates to its large models. Doubao 1.5 Deep Thinking model and Doubao Text-to-Image 3.0 model are now officially available via Volcano Engine's open APIs for developers and enterprise clients. These two models have achieved industry-leading performance in both reasoning and general tasks, and have made significant progress in visual reasoning and image generation.

ByteDance Releases Seedream 3.0 Text-to-Image Model Technical Report: Significant Performance Upgrades

ByteDance's Seed team has officially released the technical report for its Seedream 3.0 text-to-image model. This model boasts significant performance improvements, representing a native high-resolution, bilingual (English and Chinese) foundational image generation model. It achieves breakthroughs in resolution, structural accuracy of generated images, and more, showing significant advantages over the previous version. The report details Seedream 3.0's performance across various dimensions. Data in the charts are normalized using the best indicator as a reference. Seedream 3.0 natively supports...

Huawei Noah's Ark Lab and HKU Release Dream 7B, a Powerful Open-Source Diffusion Language Model

A new star shines brightly in the field of artificial intelligence! Recently, Huawei Noah's Ark Lab and the Hong Kong University Natural Language Processing Group (HKU NLP Group) jointly released a new language model called Dream7B. This model is hailed as the most powerful open-source diffusion large language model to date. Dream7B not only surpasses existing diffusion language models in performance, but also rivals or even surpasses top autoregressive (AR) language models of similar scale in general capabilities, mathematics, code, and planning abilities.

Rise of Domestic AI! The 1.7 Billion Parameter Open-Source Image Model HiDream-I1 Emerges

Where the power of code meets artistic inspiration, a new generation of artificial intelligence is quietly changing the boundaries of the creative world. Recently, the domestically-produced open-source image generation model HiDream-I1 was震撼发布, boasting 1.7 billion parameters. This AI artist, meticulously crafted by the HiDream-ai team, is rapidly becoming a tech darling. This open-source image generation tool, based on diffusion model technology, can transform text descriptions into high-quality images, demonstrating remarkable strength in detail rendering and image consistency. Preliminary tests show...