AigcPanel 1.3.0 Major Update Launches Live Streaming and Image Generation

AigcPanel is an open-source and free AI digital human system that has recently released a major version update - v1.3.0. This update not only enhances live streaming features but also adds support for as many as 384 models, truly realizing the functions of text-to-image and image-to-image, marking a new leap in creative methods.

AigcPanel is an AI tool with a friendly interface and simple operation, especially suitable for beginners. It not only supports intelligent live streaming, video synthesis, and voice synthesis, but also allows voice cloning and replacement, making it easy for users to create content. The most surprising feature is that the updated live streaming function supports selecting different model versions, allowing users to switch flexibly according to their needs, greatly improving the live streaming experience.

In this new version, AigcPanel also added a quick selection function for the size of live video content. Users can select preset sizes with one click, simplifying the preparation before live streaming. The launch of the text-to-image and image-to-image models gives users more choices in visual creation, making it easier to generate static images or edit existing images.

Additionally, the voice synthesis function has been significantly improved, allowing users to directly generate high-quality audio content and supporting direct invocation of large models, making the voice synthesis effect more realistic and natural. For creators who pursue perfect sound quality, this is undoubtedly good news.

With these updates, AigcPanel not only makes content creation more efficient, but also expands the application scenarios of AI technology. Whether in education, entertainment, or the business field, AigcPanel can help users improve the quality of their creations and promote industry development.

Runway Raises $308 Million, Valued at Over $3 Billion

AI video startup Runway has raised $308 million in a new funding round led by private equity firm General Atlantic. The funding will help Runway expand its new media ecosystem. Sources say the New York-based Runway is now valued at over $3 billion following this latest round. In addition to General Atlantic, several other prominent firms participated, including SoftBank.

Ideogram 2a Image Model Officially Launched: Faster, Cheaper AI Image Generation Breakthrough

Canadian AI image generation company Ideogram announced today the official launch of its new image model, Ideogram 2a, now available on the Ideogram website, API, and partner platforms. This launch quickly sparked discussions on X, considered a significant upgrade in the AI text-to-image field. Ideogram 2a attracts global creators and developers with its faster generation speed, lower cost, and improved graphic design and photography capabilities.

ByteDance's AI Assistant Doubao Now Supports One-Click Image Generation with Specified Text

The Intelligent AI Assistant Doubao, developed by ByteDance, has recently upgraded its text-to-image capabilities. The new feature allows users to generate images containing specified text with a single click. The relevant person in charge of the Doubao large model team pointed out that the text-to-image model of Doubao integrates LLM (Large Language Model) and DIT (Digital Image Technology) framework, optimizing its learning ability for Chinese data, and enhancing the generation capability of Chinese characters, significantly improving the generation results.

Can Diffusion Models 'Learn by Analogy'? Alibaba's IC-LoRA Enhances Image Generation Models with Contextual Memory

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.

Text-to-Image Generation is Here! Zhichu's Open Source Image Generation Model CogView3 is 10 Times Faster than SDXL!

Recently, Zhichu AI has open-sourced its latest creation—CogView3 and its upgraded version CogView-3Plus-3B, injecting new vitality into the field of text-to-image generation. The debut of CogView3 is undoubtedly a significant milestone. As the first model to achieve relay diffusion in the text-to-image generation domain, it employs a unique cascade diffusion method. This innovative approach first generates low-resolution images and then completes the final output through relay-based super-resolution technology. This not only greatly enhances...