Fooocus Upscale or Vary

The prompt to use for generating the image. Be as descriptive as possible for best results.

The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution).

The style to use.

You can choose Speed or Quality

Options: Speed, Quality, Extreme Speed, Lightning

The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you.

The sharpness of the generated image. Use it to control how sharp the generated image should be. Higher value means image and texture are sharper.

The size of the generated image. You can choose between some presets or custom height and width that **must be multiples of 8**.

Number of images to generate in one request

The LoRAs to use for the image generation. You can use up to 5 LoRAs and they will be merged together to generate the final image.

Refiner (SDXL or SD 1.5)

Options: None, realisticVisionV60B1_v51VAE.safetensors

Use 0.4 for SD1.5 realistic models; 0.667 for SD1.5 anime models 0.8 for XL-refiners; or any value for switching two SDXL models.

The format of the generated image.

Options: png, jpeg, webp

If `True`, the media will be returned as a data URI and the output data won't be available in the request history.

The same seed and the same prompt given to the same version of Stable Diffusion will output the same image every time.

The image to upscale or vary.

The method to use for upscaling or varying.

Options: Disabled, Vary (Subtle), Vary (Strong), Upscale (1.5x), Upscale (2x), Upscale (Fast 2x)

Mixing Image Prompt and Vary/Upscale

If set to false, the safety checker will be disabled.