You're looking at a specific version of this model. Jump to the model overview.
annakaz /sdxl-inference:eb0e45bd
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| Lora_url |
string
|
Load Lora model
|
|
| prompt |
string
|
An TOK riding a rainbow unicorn
|
Input prompt. If encryptedInput is true, this should be encrypted
|
| negative_prompt |
string
|
|
Input Negative Prompt
|
| enable_face_inpainting |
boolean
|
False
|
Inpaint small faces to improve resolution. Will slow down inference.
|
| inpainting_prompt |
string
|
realistic <s1><s2> man face
|
Prompt for inpainting, use <s1><s2> to refer to lora. Made this available in params just to find the right prompt
|
| inpainting_negative_prompt |
string
|
frame, mask, surgical, ui, ugly, distorted eyes, deformed iris, toothless, squint, deformed iris, deformed pupils, low quality, jpeg artifacts, ugly, mutilated
|
Prompt for inpainting, use <s1><s2> to refer to lora. Made this available in params just to find the right prompt
|
| max_face_inpaint_size |
integer
|
300
|
Max size of face to inpaint. Recommended: 135-400. If it's too high, may get weird portraits.
|
| encryptedInput |
boolean
|
False
|
Whether prompt is encrypted
|
| encryptedOutput |
boolean
|
False
|
Whether image output should be encrypted
|
| userPublicKey |
string
|
4KRWKwyJCi5RyDQ10YmTUL4yS0XkyBFpr_BeB0XGQlM=
|
The public key of the user, used to encrypt image. Only used if encryptedOutput is on
|
| image |
string
|
Input image for img2img or inpaint mode
|
|
| mask |
string
|
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted.
|
|
| width |
integer
|
768
|
Width of output image
|
| height |
integer
|
1024
|
Height of output image
|
| num_outputs |
integer
|
1
Min: 1 Max: 10 |
Number of images to output.
|
| scheduler |
string
(enum)
|
K_EULER
Options: DDIM, DPMSolverMultistep, HeunDiscrete, KarrasDPM, K_EULER_ANCESTRAL, K_EULER, PNDM |
scheduler
|
| num_inference_steps |
integer
|
35
Min: 1 Max: 500 |
Number of denoising steps
|
| guidance_scale |
number
|
7.5
Min: 1 Max: 50 |
Scale for classifier-free guidance
|
| prompt_strength |
number
|
0.8
Max: 1 |
Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image
|
| seed |
integer
|
Random seed. Leave blank to randomize the seed
|
|
| refine |
string
(enum)
|
no_refiner
Options: no_refiner, expert_ensemble_refiner, base_image_refiner |
Which refine style to use
|
| high_noise_frac |
number
|
0.8
Max: 1 |
For expert_ensemble_refiner, the fraction of noise to use
|
| refine_steps |
integer
|
For base_image_refiner, the number of steps to refine, defaults to num_inference_steps
|
|
| apply_watermark |
boolean
|
False
|
Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.
|
| lora_scale |
number
|
0.6
Max: 1 |
LoRA additive scale. Only applicable on trained models.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}