Image Processing Models

We provide several most popular stable diffusion models for scenarios like Texts2Images and Images2Images.

Before started

You should get some parameters before get started : SERVICE_ID, API_KEY and MODEL, you can find them on our dashbord (opens in a new tab).

API reference

Stable-Diffusion-XL & Stable-Diffusion-3.5

/v1/images/generate

Request Parameters

Parameter name	Type	Description	Required
model	String	Model type, default:stable-diffusion-xl-base-1.0	yes
prompt	String	Prompt to render	Yes
steps	Int	Number of diffusion steps to run. [10, 50], default:30	No
height	Int	Image resolution.multiple of 64 >= 128, default:512	No
width	Int	Image resolution.multiple of 64 >= 128, default:512	No
cfg_scale	Float	How strictly the diffusion process adheres to the prompt text .(higher values keep your image closer to your prompt) [0, 35], default: 7	No
seed	Int	Random noise seed. [0, 4294967295], default:0 (0 means random seed)	No

Response Elements

Parameter name	Type	Description
images	bytes	image/png - raw bytes

/v1/images/control

Request Parameters

Parameter name	Type	Description	Required
model	String	Model type, default:stable-diffusion-xl-base-1.0	yes
prompt	String	Prompt to render	Yes
image	File	Image file to initilize the diffusion process.	Yes
negative_prompt	String	Prompt to exclude	No
steps	Int	Number of diffusion steps to run. [10, 50], default:30	No
control_strength	Float	How much influence the init_image has on the diffusion process. [0, 1], default:0.35.	No
cfg_scale	Float	How strictly the diffusion process adheres to the prompt text.(higher values keep your image closer to your prompt) [0, 35], default: 7	No
seed	Int	Random noise seed. [0, 4294967295], default:0 (0 means random seed)	No

Response Elements

Parameter name	Type	Description
image	bytes	image/png - raw bytes

Usage

python

/v1/images/generate

import requests
import base64
 
# Define the URL and the payload to send.
url = "https://modelapi.holmesai.xyz/$SERVICE_ID/v1/images/generate"
 
# Set Authorization header
Headers = { "Authorization" : "Bearer {}".format("$API_KEY") }
 
payload = {
    "model": "$MODEL",
    "prompt": "puppy dog",
    "steps": 30,
    "height": 512,
    "width": 512,
    "cfg_scale": 10,
}
 
# Send said payload to said URL through the API.
response = requests.post(url=f'{url}', json=payload, headers=Headers, stream=True)
 
# Decode and save the image.
with open("output.png", 'wb') as f:
    for chunk in response.iter_content(chunk_size=8192):
        f.write(chunk)

/v1/images/control

import requests
import base64
import json
 
# Define the URL and the payload to send.
url = "https://modelapi.holmesai.xyz/$SERVICE_ID/v1/images/control"
 
# Set Authorization header
Headers = { "Authorization" : "Bearer {}".format("$API_KEY") }
file_path = "input.png"
 
with open(file_path, 'rb') as image_file:
    payload = {
        "model": "$MODEL",
        "prompt": "Put glassed on the dog",
        "negative_prompt": "",
        "steps": 30,
        "cfg_scale": 10,
    }
    files = {
        'image': (file_path, image_file.read(), 'application/octet-stream'),  # Binary file
        "model": "$MODEL",
    }
 
    # Send said payload to said URL through the API.
    response = requests.post(url=f'{url}', files=files, data=payload, headers=Headers)
 
    # Decode and save the image.
    with open("output.png", 'wb') as f:
        for chunk in response.iter_content(chunk_size=8192):
            f.write(chunk)

curl

/v1/images/generate

curl https://modelapi.holmesai.xyz/$SERVICE_ID/v1/images/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
        "model": "$MODEL",
        "prompt": "a cat ",
        "steps": 20,
        "height": 512,
        "width": 512,
        "cfg_scale": 10
   }' \
   -o out.png

/v1/images/control

curl -X POST https://modelapi.holmesai.xyz/$SERVICE_ID/v1/images/control \
    -F "model=$MODEL" \
    -F "prompt=add an apple" \
    -F "image=@test.png" \
    -F "negative_prompt=" \
    -F "steps=30" \
    -F "cfg_scale=10" \
    -H "Authorization: Bearer $API_KEY" \
    -o out.png

Audio Processing Models Large Language Models