FindSD.art: Upload an Image to Match with Civitai's Similar SD Models

OminiControl Art Released: Distilling Ghibli and other Art Styles from GPT-4 into the FLUX Model

ByteDance Launches AI Model Community Platform: Lumi, Similar to Liblib and Civitai

On October 31, ByteDance quietly launched an AI model sharing community platform called 'Lumi'. The platform is reported to offer features such as model upload and sharing, workflow building, and LoRA training. It is currently in the internal testing phase and is only accessible to whitelisted users.

The No-Face Artifact of Xiaohongshu! FLUX.1-dev-LoRA Perfectly Blends Illustration with Reality

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.

Civitai Launches 'Green' New Site Civitai Green - Download Models Without Sneaking Around

The launch of Civitai Green marks the platform's transformation into a clean, professional AI art creation environment, completely eliminating adult content to provide creators with safe and appropriate image and model resources, enhancing the user experience in the workplace. Through Civitai Green, the platform not only ensures the high quality and diversity of resources but also introduces a more efficient payment processor, Paddle, optimizing the user payment experience. This transformation benefits the platform's commercial development and strengthens the community ecosystem by sharing works.

Stability AI's SD3 Faces Backlash Over Licensing Issues, CivitAI Community Bans Related Content

Stability AI's latest major model, Stable Diffusion 3 (SD3), is facing strong opposition from the AI community due to its restrictive licensing terms. This controversy has led to a ban by the Stable Diffusion community center, which on Monday prohibited work related to SD3.

Comfyui Pixel Art Style Plugin PixelArt Detector Simulates Lighting Changes at Different Times

Comfyui has launched a pixel art style plugin called PixelArt Detector, introducing a new style adjustment feature for creators. This plugin can simulate lighting changes at different times of the day and provides various style presets, enriching the expressive forms of pixel art. Users can alter the color style of pixel art while maintaining the main content and layout, presenting a variety of visual effects and expanding creative possibilities. It is suitable for pixel game developers to adjust lighting effects and enhance game atmosphere, as well as for fields like animation and illustration design.

Tencent Launches ELLA Project to Enhance Understanding of Prompts for SD Models

Tencent has launched the ELLA project, which enhances the prompt understanding ability of SD models without the need for training. ELLA integrates large language models into text-to-image diffusion models, improving the model's text processing capabilities. The project team designed a time-step-aware semantic connector to help the diffusion model better comprehend text prompts. ELLA can be easily integrated into community models and tools, enhancing the ability to adhere to complex prompts. Through experimentation, ELLA has demonstrated excellent performance in handling complex prompts that involve multiple objects and different attributes.

SegMoE Model Achieves SD Model Mixture Without Training

SegMoE is an innovative method for mixing SD models without training. It offers three mixed models, consisting of 2 SDXL models, 4 SDXL models, and 4 SD1.5 models. The model adapts to various styles, but overall performance still needs improvement. The advantage of the mixed model is its ability to accommodate diverse styles, but quality and speed still require enhancement. Although SegMoE provides a novel approach, performance and effectiveness still require further improvement.

Douyin AI Image Expansion Comedy Craze: Absurd Art Style Makes Netizens Laugh

Douyin's AI image expansion has sparked a craze, transforming originally sincere photos with 'divine operations' into outrageous edits. Netizens humorously remark on the dramatic 180-degree turn in art style, making the comment section a highlight. The article showcases several examples of absurd image expansions, including 'Holding Her Feet' and 'Wishing You Happiness.' In practical tests, feeding materials from 'Empresses in the Palace' to the AI produced eye-opening results. Despite some failures, AI image expansion mostly proves effective, enhancing photo scenes and details.

AI content community Civitai secures $5.1 million in funding led by Andreessen Horowitz

👍 Platform user base: Civitai has approximately 3 million registered users with monthly active users reaching 12 to 13 million. 💰 Funding amount: Andreessen Horowitz led a $5.1 million seed round investment in Civitai. 🔥 Development plan: Civitai plans to launch a mobile app to expand the platform into more creative fields.