Search AI Products and News

Remade AI has released 8 open-source LoRAs for Wan2.1, significantly enhancing AI video creation capabilities and sparking excitement within the community.

March 9, 2025, California, USA — Open-source models are making text-to-video technology increasingly exciting. AI developer Ostris (@ostrisai) recently shared on X platform the results of his Wan2.1 LoRA model trained with his own photos. Using only about 20 photos and a consumer-grade RTX 4090 graphics card, he achieved astonishing video generation results. This achievement not only showcases the potential of open-source technology but also sparked a discussion on video LoRA training within the X community.

AI is rapidly becoming an essential tool in today's creative industries. Many tools allow users to generate stories, images, or short films with just a few words. However, Flora's founder and CEO, Weber Wong, points out that existing AI tools are mostly "designed by non-creatives for non-creatives," failing to truly meet the needs of professional creatives. Flora recently launched officially, releasing a manifesto emphasizing AI creative tools.

PhotoDoodle, a novel AI image editing system developed by ByteDance in collaboration with research teams from universities in China and Singapore, is redefining our understanding of image creation. This innovative technology, based on the Flux.1 model, can learn artistic styles from a small number of samples and accurately execute specific editing instructions, opening up new possibilities for creative expression. Built upon Flux.1, PhotoDoodle's core is the OmniEditor system, initially developed by the research team. It cleverly utilizes LoRA (Low-Rank Adaptation) to...

Kimi Smart Assistant, a subsidiary of Moon's Dark Side, announces the evolution of the Kimi Exploration Version, introducing three major inference abilities: Enhanced Search Intent, Source Analysis, and Chain Thinking. The Enhanced Search Intent capability allows Kimi Exploration Version to convert abstract and ambiguous questions into specific queries, expanding users' true search intentions. The Source Analysis capability enables Kimi Exploration Version to filter through a vast number of search results to select sources that are more authoritative and reliable, providing traceable links down to the paragraph level. The Chain Thinking capability allows Kimi Exploration Version to handle reasoning based on a chain of thought.

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.

Recently, ByteDance quietly launched an AI model sharing community called 'Lumi'. The platform integrates various functions including model sharing, workflow building, and LoRA training, although it is currently still in the internal testing phase. Product entrance: https://top.aibase.com/tool/lumi. The core highlight of Lumi is its model sharing and management features, allowing users to easily upload their developed AI models.

In the wave of digital creativity, a unique AI toy designer has quietly emerged. Toy Box Flux, an artificial intelligence model focused on generating 3D toy designs, is changing the way we conceive and create toys. It not only transforms text descriptions into vivid 3D toy visuals but also extends into the interior design realm, bringing new inspiration to spatial layouts. The uniqueness of Toy Box Flux lies in its training method. The development team has ingeniously combined existing 3D LoRA technology with original Co...

Real to cartoon is a timeless trend on social platforms, continuously evolving with new methods. For example, I just discovered this interesting Flux LoRA, which is expected to become popular on Xiaohongshu soon. This LoRA generates 4 real photos and additionally overlays a corresponding cartoon character on top. The effect is somewhat similar to the recent trending Cotton Candy Dolls on Douyin, where real photos and cartoon characters are layered together in one image, with a white outline around the cartoon character to enhance contrast.

Recently, many users reported that Kimi has begun internal testing of the "Exploration Version". Users who have obtained testing privileges can enter " / " in the input box to see the new feature options. From the screenshots of the Kimi Exploration Version interface, the page prompts: Enter " / " to use Kimi Exploration Version to solve complex search problems. It is worth mentioning that since it is in functional testing, each account with testing privileges can only use it 5 times a day. It is understood that Kimi Exploration Version has significantly improved its intelligence and reasoning capabilities.

Recently, foreign media reported that ByteDance is accelerating its efforts to self-develop and manufacture AI chips to reduce dependence on expensive chips from NVIDIA. The report claims that ByteDance plans to collaborate with TSMC and expects to mass-produce two self-developed AI chips by 2026, having already reserved the production of hundreds of thousands of chips. More notably, the report pointed out that ByteDance aims for its self-developed chip clusters to achieve four times the computing performance of a single H100 chip at a similar cost. In response, ByteDance quickly addressed this report.

Recently, a research team from Shanghai Jiao Tong University and Harvard University introduced a novel model fine-tuning method — LoRA-Dash. This new approach claims to be more efficient than existing LoRA methods, particularly in the fine-tuning of specific tasks, achieving the same results with an 8 to 16 times reduction in the number of parameters. This is undoubtedly a major breakthrough for fine-tuning tasks that require substantial computational resources. In the context of the rapid development of large-scale language models, the demand for fine-tuning specific tasks is steadily increasing. However, fine-tuning often

Fluxgym is a new training tool aimed at AI enthusiasts, designed to lower the barriers to model training. It has extremely low hardware requirements, needing only 12GB of VRAM to conduct AI model training, significantly expanding the participant base. By combining a simple front-end with a powerful back-end, Fluxgym provides an easy-to-use interface, allowing users to initiate the training process in just three simple steps. Its core advantages lie in support for low-spec devices, a simplified user interface, and a smooth training process, enabling AI newcomers to get started quickly.

FLUX.1-dev-LoRA is an innovative image generation model that specializes in merging elements of reality with illustrations to create unique visual effects. Trained based on FLUX.1-dev, it can depict foreground characters in an illustrated style while maintaining realism in the background, making it suitable for generating creative images on social platforms. Users can generate images that meet their needs by providing scene descriptions and character action prompts. Official prompt examples demonstrate how to describe for specific art style fusion. Online experience and model download links are provided.