Wenshengtu Model

In a blog post yesterday (October 22), Stability AI announced the release of Stable Diffusion 3.5, which marks a significant advancement in open source AI graphical models. Stable Diffusion 3.5 is available in Medium (released on October 29), Large and Large Turbo sizes, designed to meet the different needs of scientific researchers, enthusiasts, startups and enterprises, with the following introduction: Stable Dif...

Oct. 14, 2012 - Smart Spectrum's technical team announced today that it has open-sourced the text2img models CogView3 and CogView3-Plus-3B, and the capabilities of this series of models are now available on the Smart Spectrum Clear Words app. According to the introduction, CogView3 is a text2img model based on cascading diffusion. According to the introduction, CogView3 is a text2img model based on cascade diffusion, which consists of three stages as follows: Stage 1: Generate a 512x512 low-resolution image using the standard diffusion process. The second stage: using the relay diffusion process, the implementation of 2 times the super-resolution generation, from 512x512 ...

Zhipu AI recently released its latest large-scale model GLM-4-Plus, which demonstrates powerful visual capabilities comparable to OpenAI GPT-4, and announced that it will be open for use on August 30. Major update highlights: Language base model GLM-4-Plus: A qualitative leap in language parsing, instruction execution, and long text processing capabilities, continuing to maintain a leading position in international competition. CogView-3-Plus: The performance of the text model is comparable to the industry's top MJ-V6 and FLUX models. Image/video understanding model GLM-4V-Plus...

Introduction to FLUX Model In yesterday's article (FLUX12B shocking release: SD founding team, 23G largest open source text graph model to date), we have introduced FLUX, a dark horse text graph model. This is a 12B parameter, 23.8G weight file, the largest open source text graph model to date. This is the latest open source model launched by Black Forest Labs (the original team of Stable Diffusion). The team has strong technical strength and is a dark horse startup company that has completed a $31 million seed round of series financing. Including:…

Introduction to FLUX Model On August 1, the open source text image model entered a major milestone. The 12B text image model of Black Forest Lab (a company that has completed a $31 million seed round of series financing) was released: FLUX. This is the largest open source text image model to date. It is also the current high-quality text image model. The FLUX.1 text image model suite defines a new state-of-the-art level for text-to-image synthesis, setting a new benchmark standard in image detail, prompt following, style diversity, and scene complexity. Striking a balance between accessibility and model capabilities, FLUX…

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...

Stability AI is based on the Stable Diffusion model and has further expanded into the audio field. It has launched Stable Audio Open, which can generate high-quality audio samples based on user-entered prompts. Stable Audio Open can create up to 47 seconds of music, which is very suitable for drums, instrumental melodies, ambient sounds, and onomatopoeia. This open source model is based on the diffusion of transforms model (DiT) and operates in the latent space of the autoencoder to improve the generation of audio…

Hello everyone, I set a flag when introducing Tencent's open source Hunyuan-DiT Wenshengtu model: to publish a deployment tutorial, because my graphics card is 16G, which just meets the minimum video memory requirement. Some friends have left messages expressing their interest in this, so today, it is here! It should be noted that the computer graphics card required for this deployment must have a video memory of more than 11G. If you want to experience multiple rounds of dialogue, the video memory must be more than 32G. This tutorial will not go into details about the installation of graphics card drivers and Cuda. If you are interested, you can read my previous article: "Ubuntu22.04 …

Alibaba Research Team recently launched AtomoVideo high-fidelity image-to-video (I2V) framework, which aims to generate high-quality video content from static images and is compatible with various text-to-image (T2I) models. ▲ Image source: AtomoVIdeo team paper AtomoVideo features are as follows: High fidelity: The generated video is highly consistent with the input image in terms of details and style Motion consistency: The video moves smoothly, ensuring temporal consistency without abrupt jumps Video frame prediction: Through...

According to the official press release of Stability AI, Stability AI recently launched a new generation of text graph model called "Stable Cascade". The model is built on the Würstchen architecture and is said to be able to be easily trained and fine-tuned on consumer-grade hardware. ▲ Image source: Stability AI official press release (the same below) The official claims that compared with the industry's familiar SDXL, the new Stable Cascade model has improved performance and claimed content quality. Currently…