You're looking at a specific version of this model. Jump to the model overview.

prompthunt /cog-realvisxl2-lora-inference:f76816d7

Input

*string
Shift + Return to add a new line

Load Lora model

string
Shift + Return to add a new line

Input prompt

Default: "A photo of TOK"

string
Shift + Return to add a new line

Input Negative Prompt

Default: "plastic, blurry, grainy, [deformed | disfigured], poorly drawn, [bad : wrong] anatomy, [extra | missing | floating | disconnected] limb, (mutated hands and fingers), blurry"

file

Input image for img2img or inpaint mode

file

Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.

file

Input pose image for controlnet mode

integer

Width of output image

Default: 768

integer

Height of output image

Default: 1024

integer
(minimum: 1, maximum: 100)

Number of images to output.

Default: 1

string

scheduler

Default: "DPM++SDEKarras"

integer
(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

number
(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 3

number
(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

integer

Random seed. Leave blank to randomize the seed

string

Which refine style to use

Default: "no_refiner"

number
(minimum: 0, maximum: 1)

For expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

integer

For base_image_refiner, the number of steps to refine, defaults to num_inference_steps

number
(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

number

Amount of blur to apply to the mask.

Default: 8

number

Amount of padding (as percentage) to add to the face bounding box.

Default: 1

integer

Resize the face bounding box to this size (in pixels).

Default: 1024

string
Shift + Return to add a new line

Input inpaint prompt

Default: "A photo of TOK"

string
Shift + Return to add a new line

Input inpaint negative prompt

Default: "(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), open mouth"

number
(minimum: 0, maximum: 1)

Prompt strength when using inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.35

integer
(minimum: 1, maximum: 500)

Number of denoising steps for inpainting

Default: 25

number
(minimum: 1, maximum: 50)

Scale for classifier-free guidance for inpainting

Default: 3

number
(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.6

number

Scale for guidance for controlnet

Default: 1

boolean

Upscales face image before inpainting

Default: false

boolean

Upscales final image before returning

Default: false

boolean

Include debug output in the output

Default: true

Output

No output yet! Press "Submit" to start a prediction.