You're looking at a specific version of this model. Jump to the model overview.
zust-ai /photoshift:47b0c8b2
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
|
photoshift
|
photoshift, upscale, retouch
|
| pikeya |
string
|
|
Request Type
|
| is_premium |
boolean
|
False
|
Is this a pro user?
|
| seed |
integer
|
-1
|
Seed
|
| 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/elem/ps_elem_scene.png"}
|
Photoshift scene image
|
| photoshift_scene_subject |
string
|
[{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/ps_elem_mask.png"}]
|
Photoshift scene subject(s) image
|
| photoshift_elements |
string
|
[{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/ps_elem_elem.png"}]
|
Photoshift elements
|
| photoshift_elements_erode |
integer
|
10
|
Erode element mask
|
| photoshift_subject |
string
|
[{"left": 0, "top": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/ps_elem_sub.png"}]
|
Photoshift subject(s) image
|
| photoshift_prompt |
string
|
|
Photoshift prompt
|
| photoshift_noise |
number
|
0.65
|
Add noise to masked area
|
| photoshift_num_outputs |
integer
|
1
|
Number of generated images
|
| photoshift_reference |
number
|
0.35
|
IP-Adapter reference scale
|
| photoshift_prompt_strength |
number
|
5
|
BLIP Caption strength
|
| photoshift_resize |
boolean
|
True
|
PhotoShift (If resize the scene image)
|
| 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
|
| retouch_scene |
string
|
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene2.png"}
|
retouch scene image
|
| retouch_mask |
string
|
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/perfume_scene_subject2.png"}
|
retouch scene mask
|
| retouch_dilate |
integer
|
10
|
Dilate retouch mask
|
| retouch_prompt |
string
|
|
retouch prompt
|
| retouch_num_outputs |
integer
|
1
|
Number of generated images
|
| retouch_prompt_strength |
number
|
5
|
retouch prompt strength
|
| retouch_reference |
number
|
-1
|
retouch IP-Adapter reference
|
| enhance_scene |
string
|
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/enhance_ps_scene.png"}
|
Enhanxe scene image
|
| enhance_subject |
string
|
[{"top": 0, "left": 0, "scale": 0.0009765625, "image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/enhance_ps_sub.png"}]
|
Subject image (for overlay)
|
| enhance_subject_mask |
string
|
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/enhance_ps_mask.png"}
|
Enhance subject mask (for SAM, binary image)
|
| enhance_mask |
string
|
{"image_url": "https://raw.githubusercontent.com/zust-ai/product-ai-training/main/test/ps/elem/enhance_mask.png"}
|
Mask image (for inpaint)
|
| enhance_noise |
number
|
0.5
|
Noise for img2img
|
| enhance_prompt_strength |
number
|
4
|
Enhance prompt strength
|
| enhance_reference |
number
|
0.35
|
IP-Adapter reference
|
| enhance_use_full_canny |
boolean
|
True
|
Use full canny or not?
|
| enhance_num_outputs |
integer
|
1
|
Number of generated images
|
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'}