AI Edit Images With Brush

图片

Upload the image you would like to edit

0/1

Prompt

Describe what you want to see in the painted area

Number of Images to Generate 升级

Number of outputs to generate

1 2 3 4

Num Inference Steps 升级

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Faster generation, lower quality Slower generation, higher quality

Guidance 升级

Guidance for generated image

Very loose interpretation of the prompt Very strict adherence to the prompt

Seed 升级

Random seed. Set for reproducible generation

output_format 升级

Format of the output images

WEBP
Efficient compression, smaller file size JPG
Compressed image format PNG
Highest quality, larger file size

Output Quality 升级

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Lowest image quality Highest image quality

Lora Weights 升级

Load LoRA weights. Supports Replicate models in the format / or //, HuggingFace URLs in the format huggingface.co//, CivitAI URLs in the format civitai.com/models/[/], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

Lora Scale 升级

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Minimal or negative LoRA influence Very strong LoRA influence

Edit Images With Brush

输入

输出

我的创作