Search AI Products and News

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...

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...

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.

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...

In the field of AI art generation, diffusion models are transitioning from U-Net based architectures to Transformer-based architectures (DiT). However, the DiT ecosystem faces challenges in plugin support, efficiency, and multi-conditional control. Recently, a team led by Xiaojiu-z introduced EasyControl, an innovative framework designed to provide efficient and flexible conditional control capabilities for DiT models, effectively giving DiT models the power of ControlNet.

Diffusion models have garnered significant attention in the field of AI video generation due to their superior performance. However, their inherent iterative denoising nature leads to a time-consuming and computationally expensive generation process, significantly hindering their widespread adoption. Recently, a research team from Beihang University, the University of Hong Kong, and the Shanghai AI Laboratory jointly released AccVideo, an innovative technology. This method, employing a novel and efficient distillation approach combined with a synthetic dataset, successfully boosts the generation speed of video diffusion models by an impressive 8.5 times.

Recently, developer scraed released LanPaint on GitHub, a zero-shot image inpainting tool. This tool aims to help users achieve high-quality image inpainting results on any Stable Diffusion (SD) model, including custom-trained models. LanPaint achieves this by iteratively prompting the model to 'think' before denoising, resulting in more seamless and accurate inpainting. A key feature of LanPaint is its zero-shot capability; users can start using it immediately without any training.

A research team from New York University, MIT, and Google has recently proposed an innovative framework aimed at addressing the bottleneck of inference time scaling in diffusion models. This groundbreaking research transcends the traditional method of simply increasing the denoising steps, opening up new avenues for improving generative model performance. The framework primarily unfolds from two dimensions: one is leveraging feedback from validators, and the second is implementing algorithms to discover better noise candidates. The research team builds on a pre-trained SiT-XL model with a resolution of 256×256, maintaining 250 fixed denoising steps.

Microsoft Research has launched a powerful AI system called MatterGen that can generate new materials with specific properties, potentially accelerating the development of key technologies such as batteries and solar panels. The introduction of MatterGen signifies a fundamental shift in how scientists discover new materials. Unlike traditional methods that screen millions of existing compounds, MatterGen directly generates new materials based on desired characteristics, akin to how AI image generators create visuals from textual descriptions.

Recently, a line art coloring method called MangaNinja has garnered widespread attention, allowing users to color target line art based on reference images with just an input of the line art and the reference image. This technology is based on a diffusion model and focuses on reference-image-guided line art coloring, significantly enhancing the accuracy of coloring and interactive control capabilities. The research team employed two innovative designs to ensure precise transfer of character details. First, they introduced a patch rearrangement module to facilitate correspondence learning between the reference color images and the target line art. Secondly, they adopted a point-driven approach.

For a long time, efficiently generating high-quality, wide-angle 3D scenes from a single image has been a challenge faced by researchers. Traditional methods often rely on multi-view data or require time-consuming per-scene optimization, and they struggle with background quality and reconstruction of unseen areas. Existing technologies, when dealing with single-view 3D scene generation, often produce errors or distortions in occluded areas due to insufficient information, along with blurry backgrounds and difficulties in inferring the geometric structure of unseen regions. While regression-based models can synthesize new views in a feedforward manner, they struggle with complex...

In the field of artificial intelligence, ByteDance's commercial technology team presents the latest achievement, the Infinity model, which has become a new leader in the auto-regressive text-to-image generation domain with its outstanding performance and innovative technology. This newly open-sourced model not only surpasses Stable Diffusion 3 in image generation quality but also demonstrates significant advantages in inference speed. The core innovation of the Infinity model lies in its use of a Bitwise Token auto-regressive framework, which predicts the next level of resolution by +1 or -1.

Are you still troubled by unclear photos? A brand new image super-resolution tool called InvSR has emerged, allowing images to be instantly transformed into clear and sharp ones with minimal processing steps. The strength of this tool lies in its utilization of the rich prior knowledge embedded in large pre-trained diffusion models, achieving efficient and high-quality image resolution enhancement. The core technology of InvSR is its innovative partial noise prediction strategy. It cleverly constructs the intermediate state of the diffusion model as the starting point for the sampling process and employs a deep noise.

In the field of video analysis, the persistence of objects is an important cue for humans to understand that objects still exist even when completely occluded. However, current object segmentation methods mainly focus on visible (modal) objects, lacking the capability to handle non-modal (visible + invisible) objects. To address this issue, researchers proposed a two-stage method based on diffusion priors, Diffusion-Vas, aimed at improving the effectiveness of non-modal segmentation and content completion in videos, enabling the tracking of specified targets within the video and using diffusion models to complete the occluded parts.

Reinforcement learning has seen significant success in recent years, but its low sample efficiency limits its application in the real world. World models, as a type of environment generation model, offer hope for addressing this issue. They can serve as simulated environments to train reinforcement learning agents with higher sample efficiency. Currently, most world models simulate environment dynamics through discrete latent variable sequences. However, this method of compressing into a compact discrete representation may overlook visual details that are critical for reinforcement learning. Meanwhile, diffusion models have become prominent in the field of image generation.

Recent research from Alibaba's Tongyi Laboratory indicates that existing text-to-image Diffusion Transformer models already possess the ability to generate multiple images with specific relational contexts. With just a little 'guidance', they can achieve a synthesis of understanding and produce high-quality multi-image collections. Traditional Diffusion models are more like 'rote learning' students, requiring massive datasets to generate high-quality images. However, with the support of IC-LoRA, they become 'high-achieving students', capable of learning through analogy.

A recent study proposed a new method that leverages human attention to enhance the quality of AI-generated images. This method uses a saliency detector to identify the most important areas in the image and prioritizes the generation of these areas. Traditional image generation methods optimize the entire image uniformly, whereas the new method identifies and prioritizes more 'important' regions, similar to human attention. This approach can improve image quality and fidelity to textual prompts. Researchers utilized stable diffusion models and saliency detectors to generate images, and

At the 2024 Volcano Engine AI Innovation Roadshow, Volcano Engine President Tan Dai unveiled the latest Doubao · Video Generation Model. This model incorporates several advanced technologies, including the efficient DIT Fusion Computing Unit, which enables deep compression encoding of video and text; it also employs a novel diffusion model training approach to ensure consistency in generating multi-camera videos; in addition, the model integrates a deeply optimized Transformer architecture, significantly enhancing the generalization ability of video generation.