

Mann E Dreams
Overview :
Mann-E Dreams is the latest model from Mann-E platform, an Iranian generative AI startup based on SDXL. This model leverages thousands of mid-generated images to achieve high-quality image generation. Developed by Mann-E's founder and CEO Muhammadreza Haghiri, the team spent months collecting, annotating, and training the model. It's almost censorship-free and has been tested using Automatic1111.
Target Users :
Designed for designers, artists, and creative professionals who need to generate high-quality images. Its fast generation speed and high image quality make it an ideal choice for creative work.
Use Cases
A designer uses Mann-E Dreams to create unique advertising images.
An artist utilizes the model to generate artwork with a personal style.
Creative professionals use the model to quickly produce social media image content.
Features
CLIP Skip setting, 1 or 2 is acceptable, 1 provides better results.
Steps set to 6-10, typically 8 steps yields the best effect.
CFG Scale set within the range of 2-4.
Supports image sizes of 768x768 and 832x832, 16:9 aspect ratio can try 1080x608.
Sampler supports DPM++ SDE Karras.
Compatible with SDXL 1.0 LoRas, ControlNet, IPAdapter, InstantID and other techniques.
How to Use
1. Visit the Mann-E Dreams model page.
2. Adjust parameters such as CLIP Skip, Steps, CFG Scale as needed.
3. Select image size and sampler.
4. Input a text prompt describing the image you want to generate.
5. Click generate and wait for the model to output the image.
6. Refine the generated results until you are satisfied.
Featured AI Tools
Chinese Picks

Capcut Dreamina
CapCut Dreamina is an AIGC tool under Douyin. Users can generate creative images based on text content, supporting image resizing, aspect ratio adjustment, and template type selection. It will be used for content creation in Douyin's text or short videos in the future to enrich Douyin's AI creation content library.
AI image generation
9.0M

Outfit Anyone
Outfit Anyone is an ultra-high quality virtual try-on product that allows users to try different fashion styles without physically trying on clothes. Using a two-stream conditional diffusion model, Outfit Anyone can flexibly handle clothing deformation, generating more realistic results. It boasts extensibility, allowing adjustments for poses and body shapes, making it suitable for images ranging from anime characters to real people. Outfit Anyone's performance across various scenarios highlights its practicality and readiness for real-world applications.
AI image generation
5.3M