Hugging Face Diffusion Models
Text to Image
Image to Image
Text to Image
Image to Image
Prompt
A beautiful landscape with mountains and a lake
Negative Prompt (Optional)
blurry, low quality, distorted, deformed, ugly, pixelated, noise, grain, text, watermark, poor composition, bad proportions, disfigured, mutation, mutated, extra limbs, extra fingers, fused fingers, malformed hands, poorly drawn face, bad anatomy, amateur drawing, low resolution, duplicate, cropped, out of frame, worst quality, jpeg artifacts, compression artifacts, glitch, overexposed, underexposed, low contrast, washed out colors, oversaturated, signature, username, artist name, logo, unnatural lighting, uneven lighting, harsh shadows, motion blur, out of focus, chromatic aberration, film grain, scratches, stains, dark spots, light leaks, fuzzy edges, jagged edges, broken lines, stretched image, elongated features, asymmetrical eyes, misaligned features, missing details, incomplete rendering
Model
stabilityai/stable-diffusion-3-medium-diffusers
Guidance Scale
↺
1
20
Inference Steps
↺
10
100
Seed (Optional)
Generate Image
Generated Image
Error
Input Image
Drop Image Here
- or -
Click to Upload
Prompt
Transform this image with fantasy elements
Negative Prompt (Optional)
blurry, low quality, distorted, deformed, ugly, pixelated, noise, grain, text, watermark, poor composition, bad proportions, disfigured, mutation, mutated, extra limbs, extra fingers, fused fingers, malformed hands, poorly drawn face, bad anatomy, amateur drawing, low resolution, duplicate, cropped, out of frame, worst quality, jpeg artifacts, compression artifacts, glitch, overexposed, underexposed, low contrast, washed out colors, oversaturated, signature, username, artist name, logo, unnatural lighting, uneven lighting, harsh shadows, motion blur, out of focus, chromatic aberration, film grain, scratches, stains, dark spots, light leaks, fuzzy edges, jagged edges, broken lines, stretched image, elongated features, asymmetrical eyes, misaligned features, missing details, incomplete rendering
Use ControlNet (Depth)
Model (used only if ControlNet is disabled)
stable-diffusion-v1-5/stable-diffusion-v1-5
Guidance Scale
↺
1
20
Inference Steps
↺
10
100
Transform Image
Generated Image
Error