tonyhopkins994
/
sdxl-test
- Public
- 42 runs
Run tonyhopkins994/sdxl-test with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
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 |
|---|---|---|---|
| prompt |
string
|
Living Room
|
Input prompt
|
| negative_prompt |
string
|
blurry, distorted
|
Negative Prompt
|
| image |
string
|
Input image for img2img or inpaint mode; base64 string
|
|
| mask |
string
|
Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted; base64 string
|
|
| width |
integer
|
1024
|
Width of output image
|
| height |
integer
|
1024
|
Height of output image
|
| sizing_strategy |
string
(enum)
|
width_height
Options: width_height, input_image, controlnet_1_image, controlnet_2_image, controlnet_3_image, mask_image |
Decide how to resize images – use width/height, resize based on input image or control image
|
| num_outputs |
integer
|
1
Min: 1 Max: 6 |
Number of images to output
|
| scheduler |
string
(enum)
|
KarrasDPM
Options: DPMSolverMultistep, KarrasDPM |
scheduler
|
| num_inference_steps |
integer
|
30
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 |
string
|
-1
|
Random seed. Leave blank to randomize the seed
|
| refine |
string
(enum)
|
no_refiner
Options: no_refiner, base_image_refiner |
Which refine style 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.
|
| lora_weights |
string
|
Replicate LoRA weights to use. Leave blank to use the default weights.
|
|
| high_speed_inference |
boolean
|
False
|
Use LCM LoRA for high speed inference
|
| disable_safety_checker |
boolean
|
False
|
Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)
|
| controlnet_1 |
string
(enum)
|
none
Options: none, edge_canny, illusion, depth_leres, depth_midas, soft_edge_pidi, soft_edge_hed, lineart, lineart_anime, openpose |
Controlnet
|
| controlnet_1_image |
string
|
Input image for first controlnet, base64 encoded string
|
|
| controlnet_1_conditioning_scale |
number
|
0.75
Max: 4 |
How strong the controlnet conditioning is
|
| controlnet_1_start |
number
|
0
Max: 1 |
When controlnet conditioning starts
|
| controlnet_1_end |
number
|
1
Max: 1 |
When controlnet conditioning ends
|
| controlnet_2 |
string
(enum)
|
none
Options: none, edge_canny, illusion, depth_leres, depth_midas, soft_edge_pidi, soft_edge_hed, lineart, lineart_anime, openpose |
Controlnet
|
| controlnet_2_image |
string
|
Input image for second controlnet, base64 encoded string
|
|
| controlnet_2_conditioning_scale |
number
|
0.75
Max: 4 |
How strong the controlnet conditioning is
|
| controlnet_2_start |
number
|
0
Max: 1 |
When controlnet conditioning starts
|
| controlnet_2_end |
number
|
1
Max: 1 |
When controlnet conditioning ends
|
| controlnet_3 |
string
(enum)
|
none
Options: none, edge_canny, illusion, depth_leres, depth_midas, soft_edge_pidi, soft_edge_hed, lineart, lineart_anime, openpose |
Controlnet
|
| controlnet_3_image |
string
|
Input image for third controlnet, base64 encoded string
|
|
| controlnet_3_conditioning_scale |
number
|
0.75
Max: 4 |
How strong the controlnet conditioning is
|
| controlnet_3_start |
number
|
0
Max: 1 |
When controlnet conditioning starts
|
| controlnet_3_end |
number
|
1
Max: 1 |
When controlnet conditioning ends
|
| ip_adapter_image |
string
|
Input image for ip_adapter, base64 encoded string
|
|
| ip_adapter_scale |
number
|
0.5
|
IP adapter guidance strength
|
{
"type": "object",
"title": "Input",
"properties": {
"mask": {
"type": "string",
"title": "Mask",
"x-order": 3,
"description": "Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted; base64 string"
},
"seed": {
"type": "string",
"title": "Seed",
"default": "-1",
"x-order": 12,
"description": "Random seed. Leave blank to randomize the seed"
},
"image": {
"type": "string",
"title": "Image",
"x-order": 2,
"description": "Input image for img2img or inpaint mode; base64 string"
},
"width": {
"type": "integer",
"title": "Width",
"default": 1024,
"x-order": 4,
"description": "Width of output image"
},
"height": {
"type": "integer",
"title": "Height",
"default": 1024,
"x-order": 5,
"description": "Height of output image"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "Living Room",
"x-order": 0,
"description": "Input prompt"
},
"refine": {
"enum": [
"no_refiner",
"base_image_refiner"
],
"type": "string",
"title": "refine",
"description": "Which refine style to use",
"default": "no_refiner",
"x-order": 13
},
"scheduler": {
"enum": [
"DPMSolverMultistep",
"KarrasDPM"
],
"type": "string",
"title": "scheduler",
"description": "scheduler",
"default": "KarrasDPM",
"x-order": 8
},
"lora_scale": {
"type": "number",
"title": "Lora Scale",
"default": 0.6,
"maximum": 1,
"minimum": 0,
"x-order": 16,
"description": "LoRA additive scale. Only applicable on trained models."
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 6,
"minimum": 1,
"x-order": 7,
"description": "Number of images to output"
},
"controlnet_1": {
"enum": [
"none",
"edge_canny",
"illusion",
"depth_leres",
"depth_midas",
"soft_edge_pidi",
"soft_edge_hed",
"lineart",
"lineart_anime",
"openpose"
],
"type": "string",
"title": "controlnet_1",
"description": "Controlnet",
"default": "none",
"x-order": 20
},
"controlnet_2": {
"enum": [
"none",
"edge_canny",
"illusion",
"depth_leres",
"depth_midas",
"soft_edge_pidi",
"soft_edge_hed",
"lineart",
"lineart_anime",
"openpose"
],
"type": "string",
"title": "controlnet_2",
"description": "Controlnet",
"default": "none",
"x-order": 25
},
"controlnet_3": {
"enum": [
"none",
"edge_canny",
"illusion",
"depth_leres",
"depth_midas",
"soft_edge_pidi",
"soft_edge_hed",
"lineart",
"lineart_anime",
"openpose"
],
"type": "string",
"title": "controlnet_3",
"description": "Controlnet",
"default": "none",
"x-order": 30
},
"lora_weights": {
"type": "string",
"title": "Lora Weights",
"x-order": 17,
"description": "Replicate LoRA weights to use. Leave blank to use the default weights."
},
"refine_steps": {
"type": "integer",
"title": "Refine Steps",
"x-order": 14,
"description": "For base_image_refiner, the number of steps to refine, defaults to num_inference_steps"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7.5,
"maximum": 50,
"minimum": 1,
"x-order": 10,
"description": "Scale for classifier-free guidance"
},
"apply_watermark": {
"type": "boolean",
"title": "Apply Watermark",
"default": false,
"x-order": 15,
"description": "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."
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "blurry, distorted",
"x-order": 1,
"description": "Negative Prompt"
},
"prompt_strength": {
"type": "number",
"title": "Prompt Strength",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 11,
"description": "Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image"
},
"sizing_strategy": {
"enum": [
"width_height",
"input_image",
"controlnet_1_image",
"controlnet_2_image",
"controlnet_3_image",
"mask_image"
],
"type": "string",
"title": "sizing_strategy",
"description": "Decide how to resize images \u2013 use width/height, resize based on input image or control image",
"default": "width_height",
"x-order": 6
},
"controlnet_1_end": {
"type": "number",
"title": "Controlnet 1 End",
"default": 1,
"maximum": 1,
"minimum": 0,
"x-order": 24,
"description": "When controlnet conditioning ends"
},
"controlnet_2_end": {
"type": "number",
"title": "Controlnet 2 End",
"default": 1,
"maximum": 1,
"minimum": 0,
"x-order": 29,
"description": "When controlnet conditioning ends"
},
"controlnet_3_end": {
"type": "number",
"title": "Controlnet 3 End",
"default": 1,
"maximum": 1,
"minimum": 0,
"x-order": 34,
"description": "When controlnet conditioning ends"
},
"ip_adapter_image": {
"type": "string",
"title": "Ip Adapter Image",
"x-order": 35,
"description": "Input image for ip_adapter, base64 encoded string"
},
"ip_adapter_scale": {
"type": "number",
"title": "Ip Adapter Scale",
"default": 0.5,
"x-order": 36,
"description": "IP adapter guidance strength"
},
"controlnet_1_image": {
"type": "string",
"title": "Controlnet 1 Image",
"x-order": 21,
"description": "Input image for first controlnet, base64 encoded string"
},
"controlnet_1_start": {
"type": "number",
"title": "Controlnet 1 Start",
"default": 0,
"maximum": 1,
"minimum": 0,
"x-order": 23,
"description": "When controlnet conditioning starts"
},
"controlnet_2_image": {
"type": "string",
"title": "Controlnet 2 Image",
"x-order": 26,
"description": "Input image for second controlnet, base64 encoded string"
},
"controlnet_2_start": {
"type": "number",
"title": "Controlnet 2 Start",
"default": 0,
"maximum": 1,
"minimum": 0,
"x-order": 28,
"description": "When controlnet conditioning starts"
},
"controlnet_3_image": {
"type": "string",
"title": "Controlnet 3 Image",
"x-order": 31,
"description": "Input image for third controlnet, base64 encoded string"
},
"controlnet_3_start": {
"type": "number",
"title": "Controlnet 3 Start",
"default": 0,
"maximum": 1,
"minimum": 0,
"x-order": 33,
"description": "When controlnet conditioning starts"
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 30,
"maximum": 500,
"minimum": 1,
"x-order": 9,
"description": "Number of denoising steps"
},
"high_speed_inference": {
"type": "boolean",
"title": "High Speed Inference",
"default": false,
"x-order": 18,
"description": "Use LCM LoRA for high speed inference"
},
"disable_safety_checker": {
"type": "boolean",
"title": "Disable Safety Checker",
"default": false,
"x-order": 19,
"description": "Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)"
},
"controlnet_1_conditioning_scale": {
"type": "number",
"title": "Controlnet 1 Conditioning Scale",
"default": 0.75,
"maximum": 4,
"minimum": 0,
"x-order": 22,
"description": "How strong the controlnet conditioning is"
},
"controlnet_2_conditioning_scale": {
"type": "number",
"title": "Controlnet 2 Conditioning Scale",
"default": 0.75,
"maximum": 4,
"minimum": 0,
"x-order": 27,
"description": "How strong the controlnet conditioning is"
},
"controlnet_3_conditioning_scale": {
"type": "number",
"title": "Controlnet 3 Conditioning Scale",
"default": 0.75,
"maximum": 4,
"minimum": 0,
"x-order": 32,
"description": "How strong the controlnet conditioning is"
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "array",
"items": {
"type": "string"
},
"title": "Output"
}