zsxkib
/
flux-caricature
- Public
- 611 runs
Run zsxkib/flux-caricature 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
|
Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
|
|
| image |
string
|
Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
|
|
| mask |
string
|
Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
|
|
| aspect_ratio |
string
(enum)
|
1:1
Options: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21, custom |
Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
|
| height |
integer
|
Min: 256 Max: 1440 |
Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
|
| width |
integer
|
Min: 256 Max: 1440 |
Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
|
| prompt_strength |
number
|
0.8
Max: 1 |
Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
|
| model |
string
(enum)
|
dev
Options: dev, schnell |
Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
|
| num_outputs |
integer
|
1
Min: 1 Max: 4 |
Number of outputs to generate
|
| num_inference_steps |
integer
|
28
Min: 1 Max: 50 |
Number of denoising steps. More steps can give more detailed images, but take longer.
|
| guidance_scale |
number
|
3
Max: 10 |
Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
|
| seed |
integer
|
Random seed. Set for reproducible generation
|
|
| output_format |
string
(enum)
|
webp
Options: webp, jpg, png |
Format of the output images
|
| output_quality |
integer
|
80
Max: 100 |
Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
|
| disable_safety_checker |
boolean
|
False
|
Disable safety checker for generated images.
|
| go_fast |
boolean
|
False
|
Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
|
| megapixels |
string
(enum)
|
1
Options: 1, 0.25 |
Approximate number of megapixels for generated image
|
| lora_scale |
number
|
1
Min: -1 Max: 3 |
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.
|
| extra_lora |
string
|
Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
|
|
| extra_lora_scale |
number
|
1
Min: -1 Max: 3 |
Determines how strongly the extra 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.
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"mask": {
"type": "string",
"title": "Mask",
"format": "uri",
"x-order": 2,
"description": "Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored."
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 11,
"description": "Random seed. Set for reproducible generation"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 1,
"description": "Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored."
},
"model": {
"enum": [
"dev",
"schnell"
],
"type": "string",
"title": "model",
"description": "Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.",
"default": "dev",
"x-order": 7
},
"width": {
"type": "integer",
"title": "Width",
"maximum": 1440,
"minimum": 256,
"x-order": 5,
"description": "Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation"
},
"height": {
"type": "integer",
"title": "Height",
"maximum": 1440,
"minimum": 256,
"x-order": 4,
"description": "Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 0,
"description": "Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image."
},
"go_fast": {
"type": "boolean",
"title": "Go Fast",
"default": false,
"x-order": 15,
"description": "Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16"
},
"extra_lora": {
"type": "string",
"title": "Extra Lora",
"x-order": 19,
"description": "Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'"
},
"lora_scale": {
"type": "number",
"title": "Lora Scale",
"default": 1,
"maximum": 3,
"minimum": -1,
"x-order": 18,
"description": "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."
},
"megapixels": {
"enum": [
"1",
"0.25"
],
"type": "string",
"title": "megapixels",
"description": "Approximate number of megapixels for generated image",
"default": "1",
"x-order": 16
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 8,
"description": "Number of outputs to generate"
},
"aspect_ratio": {
"enum": [
"1:1",
"16:9",
"21:9",
"3:2",
"2:3",
"4:5",
"5:4",
"3:4",
"4:3",
"9:16",
"9:21",
"custom"
],
"type": "string",
"title": "aspect_ratio",
"description": "Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode",
"default": "1:1",
"x-order": 3
},
"output_format": {
"enum": [
"webp",
"jpg",
"png"
],
"type": "string",
"title": "output_format",
"description": "Format of the output images",
"default": "webp",
"x-order": 12
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 3,
"maximum": 10,
"minimum": 0,
"x-order": 10,
"description": "Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5"
},
"output_quality": {
"type": "integer",
"title": "Output Quality",
"default": 80,
"maximum": 100,
"minimum": 0,
"x-order": 13,
"description": "Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs"
},
"prompt_strength": {
"type": "number",
"title": "Prompt Strength",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 6,
"description": "Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image"
},
"extra_lora_scale": {
"type": "number",
"title": "Extra Lora Scale",
"default": 1,
"maximum": 3,
"minimum": -1,
"x-order": 20,
"description": "Determines how strongly the extra 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."
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 28,
"maximum": 50,
"minimum": 1,
"x-order": 9,
"description": "Number of denoising steps. More steps can give more detailed images, but take longer."
},
"disable_safety_checker": {
"type": "boolean",
"title": "Disable Safety Checker",
"default": false,
"x-order": 14,
"description": "Disable safety checker for generated images."
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
}