You're looking at a specific version of this model. Jump to the model overview.

qwen /qwen-edit-multiangle:bc2d4cdc

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
aspect_ratio
None
match_input_image
Aspect ratio for the generated image
output_format
None
webp
Format of the output images
seed
integer
Random seed. Set for reproducible generation
image
string
Legacy alias for image URLs. Accepts a single URL or JSON list.
prompt
string
Text instruction on how to edit the given image.
go_fast
boolean
True
Run faster predictions with additional optimizations.
image_urls
string
Optional URL or JSON list of URLs/data URIs to load as reference images.
extra_prompt
string
Optional additional text appended before the user prompt.
move_forward
integer
0

Max: 10

Move the camera forward (zoom in). Higher values push towards a close-up.
camera_prompt
string
Optional camera instruction to override automatic prompt building.
image_uploads
array
[]
Image files uploaded to Cog (jpeg, png, gif, or webp).
vertical_tilt
integer
0

Min: -1

Max: 1

Vertical camera tilt. -1 = top-down, 1 = low-angle view.
output_quality
integer
95

Max: 100

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
rotate_degrees
integer
0

Min: -180

Max: 180

Camera rotation in degrees. Positive rotates left, negative rotates right.
use_wide_angle
boolean
False
Switch to a wide-angle lens instruction.
use_multiple_angles
boolean
True
Enable the multi-angle LoRA instructions (applies only when go_fast is true).
disable_safety_checker
boolean
False
Disable safety checker for generated images.
multiple_angles_source
string
dx8152/Qwen-Edit-2509-Multiple-angles
Hugging Face repo ID/URL or local path for the multi-angle LoRA.
multiple_angles_weight
number

Max: 2

Optional override for the multi-angle LoRA weight (0 disables its influence, 1 keeps the default).
multiple_angles_weight_name
string
镜头转换.safetensors
Optional filename within the LoRA repo (defaults to 镜头转换.safetensors when using the provided repo).

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'}