Search AI Products and News

On June 6th, the Seed team of ByteDance officially released the image editing model SeedEdit3.0. This new version of the image editing model has made significant progress in maintaining the subject in images, processing background details, and following instructions, greatly improving the usability and efficiency of image editing. SeedEdit3.0 is developed based on the text-to-image model Seedream3.0, introducing diversified data fusion methods and specific reward models to address previous challenges faced by image editing models in preserving both the subject and background as well as following instructions.

Recently, Vidu AI and ComfyUI have launched a new collaboration, bringing creators a new experience from image to video creation. The Vidu API node will be officially launched on ComfyUI soon, enabling easy image-to-video generation and upgrading the creative process again. For creators, mastering new features quickly is crucial. This collaboration provides clear operational guidance: creators first need to update ComfyUI or the ComfyUI desktop version, then log in and purchase corresponding points, next go to the 【Workflow】, view the 【Browse model】

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...

Alibaba recently launched the new AI portrait generation project EcomID, along with its native implementation plugin for ComfyUI. This tool marks a significant breakthrough in the currently popular AI portrait generation field, perfectly inheriting the advantages of InstantID and PulID while achieving innovations in several key metrics. On a technical level, EcomID employs an innovative architectural design. The project draws inspiration from PuLID's ID-Encoder and cross-attention components, significantly reducing training loss through alignment.

Recently, a revolutionary plugin named ComfyUI-Detail-Daemon has been making waves in the AI drawing community. Developed by Jonseed, this tool cleverly ported the sd-webui-Detail-Daemon to the ComfyUI platform, providing creators with an unprecedented detail optimization experience. The most striking feature of this plugin is its powerful detail enhancement capability. By precisely adjusting the sigma parameter, it not only significantly improves image details but also intelligently removes excess elements.

FLUX-Controlnet-Inpainting, an image repair tool based on ControlNet and FLUX.1-dev, is redefining our understanding of image restoration. This tool not only inherits the high-quality image generation capabilities of the FLUX.1-dev model but also cleverly integrates the strengths of ControlNet. It can accurately repair images based on information from edges, sketches, depth maps, etc., generating content that harmonizes with the surrounding environment in specified areas.

Meitu has announced that its AI short film creation tool MOKI is now officially open to all users. Users can now log in to the MOKI official website (www.moki.cn) to experience this innovative tool. Unlike other video creation tools on the market, MOKI focuses on AI short film creation and covers various types of video content production, including animated shorts, online drama, story picture books, and music videos. This tool provides a comprehensive AI short film creation solution tailored to industry needs.

ComfyUI version 0.2.0 introduces Flux ControlNets technology, including Canny and Union control nets, significantly enhancing image processing capabilities. The optimized queue management features, new 'Go-to Node' for quick navigation, 'Contain' image display, and task output folder view, greatly improve work efficiency. Enhanced node library functionalities such as bookmarks, recursive expand/collapse, and search filters make resource management easier. The user interface and experience have been completely revamped.

A plugin named 'SD Monetization Treasure' for ComfyUI has recently stirred discussion in the industry. Its main feature is the one-click conversion of creative works into multiple formats, along with built-in payment functionalities to help creators seamlessly transition from content to commercialization. This plugin is particularly suitable for creators in short video platforms, supporting batch generation and video processing of multimedia content, thus enriching content presentation forms. In terms of security, SD Monetization Treasure optimizes updates to effectively prevent data leakage, resolve network connectivity issues, and ensure stable usage. It boasts excellent cross-platform compatibility.

Comfy Org has made significant progress in technological innovation, with in-depth revisions and updates addressing the original issues of ComfyUI. Support for Flux models (including Flux.1-Dev and Flux.1-Schnell) has been added, along with the integration of Tencent's Hunyuan DiT model, which significantly enhances AI image generation capabilities and expands multilingual support. The fourth stable version of ComfyUI, v0.0.4, has been released, and it is recommended for use in production environments to ensure system stability.

The ComfyUI of Aliyun PAI Artlab has introduced a workflow for creating Olympic highlight moment posters, allowing users to generate personalized Olympic-themed posters in just three steps. PAI-ArtLab is a one-stop AIGC design platform that offers dataset management, model training, and AI drawing functions, with over 200 mainstream AI generation models built-in. Users can upload local datasets for labeling or training, invoke preset AI models, or use tools such as WebUI, ComfyUI, and Khoya.

AuraSR, a colossal upsampling model with 600 million parameters, is derived from the GigaGAN paper and is now fully open-sourced. The strength of this model lies in its ability to enlarge images by four times while supplementing details that may be lost during the magnification process. Moreover, this is not all it can do; it can even perform multiple magnifications on images, enriching the details further.

Hallo, an open source project by Fudan University that generates speaking videos based on audio and images, has now integrated with the ComfyUI plugin. Although the installation process requires a significant number of dependencies and has a relatively high barrier to entry, the emergence of this open source ecosystem offers more possibilities and enjoyment for subsequent transformation and other processes.

On June 12, the SD3 Medium model will officially be open-sourced, allowing everyone to experience more realistic textures, better compositions, superior performance, and outstanding fine-tuning capabilities. In anticipation of this important moment, ComfyUI has completed adaptation work in advance, preparing for the arrival of the new model.