zust-ai/zust-diffusion

auto1111_ds8

  • Public
  • 57.3K runs

Run zust-diffusion 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
is_heartbeat
boolean
False
Check if Server Alive
with_detail
boolean
False
Detailed Output
pipe_type
string
zust_xl
SAM, photoshift, zust_fashion, zust_xl, upscale, enhance, cleanup
photoshift_cleanup_background
boolean
True
PhotoShift (Clean source image subject)
photoshift_scene
string
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
Photoshift scene image
photoshift_scene_subject
string
Photoshift scene subject(s) image
photoshift_subject
string
[{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_raw2.png"}]
Photoshift subject(s) image
photoshift_prompt
string
Photoshift prompt
photoshift_noise
number
0.65
Add noise to masked area
photoshift_reference
number
0.35
IP-Adapter reference scale
photoshift_prompt_strength
number
1
BLIP Caption strength
photoshift_resize
boolean
True
PhotoShift (If resize the scene image)
tags
string
Product Tags (jewellery, topdown)
width
integer
1024
Width
height
integer
1024
height
prompt
string
a handbag on a sofa in a sunlit living room with a bookshelf, plush rug, and a framed painting on the wall
Prompt
negative_prompt
string
Negative Prompt
subjects
string
[{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/zust_product/handbag_square.png"}]
Subject positions & URLs
is_premium
boolean
False
Is this a pro user?
controlnet_weight
number
0.65
Controlnet weight for the firstpass
controlnet_guidance_end
number
0.8
Controlnet guidance end for the firstpass
hires_noise
number
0.5
Noise strength for hires.fix
hires_guidance_scale
number
5
Prompt strength for inpaint.fix
fashion_subject
string
{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/zust_fashion/fashion_sq.png"}
Subject positions & URLs
fashion_mask
string
{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/zust_fashion/fashion_sq_mask.png"}
Fashihon pose
enhance_subject
string
[{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/enhance/enhance_sub.png"}]
Subject data (this shouldn't change)
enhance_scene
string
{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/enhance/scene_to_be_enhanced.png"}
Scene to be enhanced
enhance_reference
number
0.25
IP-Adapter strength of scene. If 0 no Reference
enhance_noise
number
0.5
Noise to be added in the scene
enhance_prompt
string
Enhanced Prompt
enhance_negative_prompt
string
Negative Prompt
upscale_url
string
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
Upscale the Image
upscale_by
integer
2
Upscaling factor
sam_url
string
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
Get SAM Embeddings
pikeya
string
Request Type
cleanup_data
string
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png", "mask": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene_subject2.png"}
Image URL to be cleaned

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'}