Stable Diffusion3

Stability AI releases more permissive Stable Diffusion3 license amid recent controversy, but is it enough? Stability AI introduced restrictive new licensing terms last month, sparking backlash from Stable Diffusion users. However, the company announced late Friday that it has relaxed the terms, to mixed reactions from users. Stability AI has released an improved community license for its Stable Diffusion3 (SD3) models…

In the latest news, the famous open source big model platform Stability AI has modified the community license agreement to allow the latest released text graph model Stable Diffusion3Medium (SD3-M) to be used commercially. This change means that individual developers and start-ups can use this powerful big model for free, bringing positive development opportunities to the industry. According to the new agreement, as long as the annual income of enterprises or individual developers is less than 1 million US dollars, they can apply to Stability AI for free commercial use of SD3-M...

I will not elaborate on the advantages of Stable diffusion 3. Here I will mainly talk about how ordinary users can deploy it locally. Currently, the SD3 model has been open sourced on HuggingFace. The address is: https://huggingface.co/stabilityai/stable-diffusion-3-medium. However, you need to log in to your Hugging Face account and sign a license agreement to download the model. After signing, you can see the file list of the entire project.

Introduction to Photographic Composition and Angle In the field of real-life photography, creating excellent photographic images involves many key technical elements, such as the choice of light and shadow effects, photographic composition (camera position: the distance between the camera and the subject) and photographic angle (the position of the camera relative to the subject). These core elements are also extremely important for the creation of AIGC drawings (Stable Diffusion 1.5/XL, Playground, Midjourney). Therefore, this article summarizes the AIGC drawing prompts related to the commonly used photography composition and angle topics,…

Recently, Stability AI announced the launch of a new set of API services, aiming to provide more comprehensive and efficient image processing services. This move will undoubtedly bring a revolution to the field of image processing. Details: https://stability.ai/news/image-services-on-stability-ai-developer-platform This set of API services includes the following main functions: First, it provides the latest image processing services of Stable Diffusion3…

The latest news is that the first batch of invitation test qualifications for SD3 have been issued, and the model weights are expected to be released next month. The official said that the scale will be gradually expanded and more test qualifications will be issued soon. Previously, Stability AI released a technical report on SD3, revealing more details of SD3. SD3 surpasses all current open source and commercial models in terms of typesetting quality, aesthetic quality, and prompt word understanding. The report introduces SD3's new multimodal diffusion Transformer architecture MMDiT, which improves the system's understanding and spelling of text. SD3 uses the correction flow RF formula, and in training...

Stability AI recently released a technical report on their most powerful image generation model, Stable Diffusion3 (SD3), revealing more details of SD3. According to Stability AI, SD3 surpasses all current open source and commercial models in terms of typography quality, aesthetic quality, and prompt word understanding, and is currently the most powerful image generation model. The key points of the technical report are as follows: According to human preference evaluation, SD3 is superior to the most advanced text-generated image systems in terms of typography quality and understanding of prompts, such as…

Stability AI recently updated its product page, inviting users to test the text-to-image generation model Stable Diffusion 3. Officials said that the new version has greatly improved the ability to handle complex prompt words, generate higher-quality images, and correct spelling errors. Stable Diffusion 3 is not currently open for testing, but an early preview program has been launched. Users can visit the page to submit relevant information and join the waiting list to test the model and provide feedback before the official release. Stability Diff…