Skip to main content

SDXL

You can use adapters to fix hands, fingers, faces or any deformaties. One of the most commonly used application of Adaper is to lock face and generate same face in any environments. Other applications include fixing hands, fingers and adding details to a specific image.

To use adapters, you will need to pass three extra parameters - adapter name, ip adapter image and scale of the adapter

Tip
  • Use only face as input image instead of the full body while using face adapters.
  • Supports only foundation SDXL model right now. Support for SDXL checkpoint is coming soon.

import requests
import json
url = "https://api.imagepipeline.io/sdxl/text2image/v1"
headers = {
"API-Key": "Your API Key"
}
data = {
"model_id": "sdxl",
"prompt": "cinematic still woman holding mango juice. emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy holding a glass of mango juice,",
"negative_prompt": "error, cropped, worst quality, low quality, duplicate, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, blurry, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck",
"num_inference_steps": 20,
"ip_adapter": ["ip-adapter-plus_sdxl_vit-h"],
"ip_adapter_scale": [0.6],
"ip_adapter_style_images": [], //For multi-ip-adapter
"ip_adapter_image": "https://www.keep-calm-and-eat-ice-cream.com/wp-content/uploads/2022/08/Ice-cream-sundae-hero-11.jpg",
"server_id": "", //For enterprise users only
"samples": 1,
"guidance_scale": 7.5,
"width": 1024,
"height": 1024
}

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json())

JSON Parameters

ParameterPermissible valuesNotes
model_idstronly accepts sdxl
promptstr, 75 tokensCheck our Prompt Guide for tips
negative_promptstr, 75 tokensCheck our Prompt Guide for tips
num_inference_stepsint, [1-100]Noise is removed with each step, resulting in a higher-quality image over time. Ideal value 20-30
strengthfloat, [0-1]Optional denoise strength
samplesint, [1-4]Generates a maximum of 4 samples per API call
guidance_scalefloat, [1-20]Higher guidance scale prioritizes text prompt relevance but sacrifices image quality. Ideal value 7.5-12.5
widthintWidth in pixels. Lower than or equal to 1024 for best results
heightintHeight in pixels. Lower than or equal to 1024 for best results
ip_adapterstr, array Model id of adapters to be used. You can add multiple by comma separated values. Allowed values are: ip-adapter_sdxl, ip-adapter_sdxl_vit-h, ip-adapter-plus_sdxl_vit-h, ip-adapter-plus-face_sdxl_vit-h
ip_adapter_scalefloat, array[0-1]How much adapters should guide the generations. You can add multiple by comma separated values.
ip_adapter_imagestrInput image to the primary adapter model. Mostly used for face lock
ip_adapter_style_imagesstr, arrayImages to be used by multi IP-adapters for usecases like style transfer or image mixing

Status

Your response will include a status.

  • If the status = SUCCESS, you will also have download_urls that will have the links to your generated image based on the number of samples you have entered. The maximum number of samples that can be generated is 4.
  • If the status = PENDING, you will receive a id. You can use the status endpoint to fetch your image using the id.
  • If the status = FAILURE, you will receive only an error message.

Endpoint: [GET]

  • https://api.imagepipeline.io/sdxl/text2image/v1/status/{{id}}

Pass the API-Key as the authorization in the header.

{
"model_id": "sdxl",
"prompt": "cinematic still woman holding mango juice. emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope",
"negative_prompt": "error, cropped, worst quality, low quality, duplicate, bad proportions, incomplete subject",
"num_inference_steps": 20,
"samples": 4,
"guidance_scale": 7.5,
"width": 1024,
"height": 1024,
"ip_adapter": ["ip-adapter-plus-face_sdxl_vit-h"],
"ip_adapter_scale": [0.6],
"ip_adapter_image": "https://t4.ftcdn.net/jpg/06/44/30/09/360_F_644300965_7asrChyeknn9fA0GuYrmIUFSBHR5HTpo.jpg"

}