🎨 Image Generation

Stable Diffusion v1.5

Classic Stable Diffusion v1.5 for high-quality text-to-image generation. Supports LoRA weights, embeddings, and custom image sizes. Generate 1-8 images with advanced CFG control and prompt expansion

Example Output

Prompt

"photo of a rhino dressed suit and tie sitting at a table in a bar with bar stools"

Generated Result

Generated

Input Parameters

Detailed text prompt for image generation *

photo of a rhino dressed suit and tie sitting at a table in a bar...

Negative prompt to avoid unwanted elements

cartoon, illustration, animation, ugly, deformed...

The size of the generated image. Width and height must be between 1024 and 4096

Default

Inference steps (1-50). Higher = better quality

Enter inference steps (1-50). higher = better quality

CFG scale (0-20). How closely to follow prompt

Enter cfg scale (0-20). how closely to follow prompt

Number of images to generate (1-8)

Enter number of images to generate (1-8)

Output format

JPEG

Expand prompt with additional details

Enable content safety checker

Try Now - Sign in to Use

More Image Generation Models

MiniMax Image-01

Minimax's first image model with character reference support

xAI Grok 2 Image

Generate vivid, realistic images based on a text prompt. Excels at generating images for marketing, social media, and entertainment. Powered by xAI's Grok technology

Midjourney Text to Image

Create stunning, high-quality images from text prompts using Midjourney's powerful AI. Always generates 4 unique variations for each prompt. Known for exceptional artistic quality and creative interpretation