You're looking at a specific version of this model. Jump to the model overview.
zust-ai /zust-diffusion:f22d8881
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 |
---|---|---|---|
is_heartbeat |
boolean
|
False
|
Check if Server Alive
|
pipe_type |
string
|
sdxl
|
sdxl or cleanup or photoshift
|
cleanup_background |
boolean
|
True
|
PhotoShift (Clean source image subject)
|
photoshift_scene_url |
string
|
https://ik.imagekit.io/zustai/Photoshift/test_ps_scene.png
|
Photoshift scene image URL
|
photoshift_subject |
string
|
{"top": 0.3818359375, "left": 0.3642578125, "scale": 0.0009765625, "image_url": "https://ik.imagekit.io/zustai/Photoshift/test_ps_sub.png"}
|
Photoshift subject image
|
with_detail |
boolean
|
False
|
Detailed Output
|
seed |
integer
|
Seed
|
|
subjects |
string
|
[{"top": 0.3583984375, "left": 0.546875, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_subject.png"}]
|
Subject Placement & URLs
|
width |
integer
|
1024
|
Width (1024, 1216, 832)
|
height |
integer
|
1024
|
Height (1024, 832, 1216)
|
prompt |
string
|
trolley suitcase on a mountain rock with hot air balloons in the blue sky
|
Prompt
|
negative_prompt |
string
|
floating objects, levitate, ugly, blur, text, signature, watermark, bad quality, lowres, worst quality, drawing
|
Negative Prompt
|
num_images_per_prompt |
integer
|
2
Min: 1 |
Number of Generations (Firstpass)
|
firstpass_inference_steps |
integer
|
20
Min: 1 |
Firstpass Iterations
|
firstpass_prompt_strength |
number
|
5
Min: 1 |
Firstpass Prompt Strength
|
firstpass_subject_control_strength |
number
|
0.5
Max: 2 |
Subject ControlNet Guidance (Firstpass)
|
inpaint_fix_inference_steps |
integer
|
30
Min: 1 |
Inpaint.fix Iterations
|
inpaint_fix_prompt_strength |
number
|
5
Min: 1 |
Inpaint.fix Prompt Strength
|
inpaint_fix_subject_control_strength |
number
|
1
Max: 2 |
Subject ControlNet Guidance (Inpaint.fix)
|
inpaint_fix_noise_strength |
number
|
0.6
|
Hires Noise Strength
|
hires_fix_erode |
integer
|
5
|
Hires.fix Erosion Kernel
|
fashion_width |
integer
|
512
|
Width (512, 768, 512)
|
fashion_height |
integer
|
512
|
Height (512, 512, 768)
|
fashion_prompt |
string
|
A beautiful wearing a short dress walking down a city street
|
Fashion Prompt
|
fashion_subjects |
string
|
[{"top": 0.251953125, "left": 0.248046875, "scale": 0.0015370747041420119, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_fashion_dress.png"}]
|
Subject Placement & URLs (Fashion)
|
fashion_keypoints |
string
|
{"top": 0, "left": 0, "scale": 0.001953125, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/test_fashion_pose.png"}
|
Keypoint Placement & URL (Fashion)
|
fashion_erode_kernel |
integer
|
7
|
Fashion Hires.fix Erosion Kernel
|
fashion_noise_strength |
number
|
0.6
|
Fashion Hires.fix Noise Strength
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}