ReplicateText to imageComing soon

qwen/qwen-image

Name: qwen/qwen-image
Brand: Replicate

qwen/qwen-image is a text to image tool from Replicate that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.0325 per image.

Limits

Runs: In the background
Returns: image
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Prompt for generated image
`seed`	number (whole)	—	Random seed. Set for reproducible generation
`image`	URL or file	—	Input image for img2img pipeline
`go_fast`	true or false	true	Run faster predictions with additional optimizations.
`guidance`	number 0 to 10	3	Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
`strength`	number 0 to 1	0.9	Strength for img2img pipeline
`image_size`	JSON	optimize_for_quality	Image size for the generated image
`lora_scale`	number	1	Determines how strongly the main LoRA should be applied.
`aspect_ratio`	JSON	16:9	Aspect ratio for the generated image
`lora_weights`	text	—	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`	JSON	webp	Format of the output images
`enhance_prompt`	true or false	false	Enhance the prompt with positive magic.
`output_quality`	number (whole) 0 to 100	80	Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
`negative_prompt`	text		Negative prompt for generated image
`extra_lora_scale`	list	—	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.
`replicate_weights`	text	—	Load LoRA weights from Replicate training. Only works with text to image pipeline. Supports arbitrary .safetensors URLs, tar files, and zip files from the Internet.
`extra_lora_weights`	list	—	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`	number (whole) 1 to 50	30	Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "qwen/qwen-image",
    "input": {
      "prompt": "<prompt>"
    }
  }'