Skip to main content
POST
/
generation
/
qwen
/
qwen-image
Qwen Image
curl --request POST \
  --url https://open.ppt.video/api/v1/generation/qwen/qwen-image \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>"
}
'
{
  "id": "<string>",
  "status": "starting"
}
Qwen image generation model

Authorizations

​
Authorization
string
header
required

API Key for API endpoints

Body

application/json
​
prompt
string
required

Prompt for generated image

​
webhook
string<uri>

Webhook URL for receiving updates

​
seed
integer | null

Random seed. Set for reproducible generation

Required range: -9007199254740991 <= x <= 9007199254740991
​
image
string<uri>

Input image for img2img pipeline

​
go_fast
boolean
default:true

Run faster predictions with additional optimizations.

​
guidance
number
default:3

Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5

Required range: 0 <= x <= 10
​
strength
number
default:0.9

Strength for img2img pipeline

Required range: 0 <= x <= 1
​
image_size
enum<string>
default:optimize_for_quality

Image size for the generated image

Available options:
optimize_for_quality,
optimize_for_speed
​
lora_scale
number
default:1

Determines how strongly the main LoRA should be applied.

​
aspect_ratio
enum<string>
default:16:9

Aspect ratio for the generated image

Available options:
1:1,
16:9,
9:16,
4:3,
3:4,
3:2,
2:3
​
lora_weights
string | null

Load LoRA weights. Only works with text to image pipeline. Supports arbitrary .safetensors URLs, tar files, and zip files from the Internet (for example, 'https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors', 'https://example.com/lora_weights.tar.gz', or 'https://example.com/lora_weights.zip')

​
output_format
enum<string>
default:webp

Format of the output images

Available options:
webp,
jpg,
png
​
enhance_prompt
boolean
default:false

Enhance the prompt with positive magic.

​
output_quality
integer
default:80

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

Required range: 0 <= x <= 100
​
negative_prompt
string
default:

Negative prompt for generated image

​
extra_lora_scale
number[] | null

Scales for additional LoRAs as an array of numbers (e.g., [0.5, 0.7]). Must match the number of weights in extra_lora_weights.

​
extra_lora_weights
string[] | null

Additional LoRA weights as an array of URLs. Same formats supported as lora_weights (e.g., ['https://huggingface.co/flymy-ai/qwen-image-lora/resolve/main/pytorch_lora_weights.safetensors', 'https://huggingface.co/flymy-ai/qwen-image-realism-lora/resolve/main/flymy_realism.safetensors'])

​
num_inference_steps
integer
default:30

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Required range: 1 <= x <= 50
​
disable_safety_checker
boolean
default:false

Disable safety checker for generated images.

Response

Generation status

​
id
string
required

Generation id.

​
status
enum<string>
required

Generation status

Available options:
starting,
processing,
succeeded,
failed,
canceled