ReplicateImage to imageComing soon

qwen/qwen-edit-multiangle

qwen/qwen-edit-multiangle is an image 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

$0.039 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

FieldKindDefaultDescription
image requiredURL or file—Image file uploaded to Cog (jpeg, png, gif, or webp).
seednumber (whole)—Random seed. Set for reproducible generation.
prompttextOptional text instruction appended after the camera directive.
go_fasttrue or falsetrueIf num_inference_steps is omitted, true runs the 4-step fast preset and false runs the 40-step detailed preset.
lora_scalenumber
0 to 4
1.25Strength applied to the selected LoRA.
aspect_ratioJSONmatch_input_imageAspect ratio for the generated image
lora_weightstextdx8152/Qwen-Edit-2509-Multiple-anglesLoRA weights to apply. Pass a Hugging Face repo slug like 'dx8152/Qwen-Edit-2509-Multiple-angles' or a direct .safetensors/zip/tar URL (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').
move_forwardnumber (whole)
0 to 10
0Move the camera forward (zoom in). Higher values push toward a close-up framing.
output_formatJSONwebpFormat of the output images.
vertical_tiltnumber (whole)
-1 to 1
0Vertical camera tilt. -1 = bird's-eye, 0 = level, 1 = worm's-eye.
output_qualitynumber (whole)
0 to 100
95Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs.
rotate_degreesnumber (whole)
-90 to 90
0Camera rotation in degrees. Positive rotates left, negative rotates right.
use_wide_angletrue or falsefalseSwitch to a wide-angle lens instruction.
num_inference_stepsnumber (whole)
1 to 40
—Explicit denoising step count (1-40). Leave blank to use the go_fast presets (4 or 40 steps).
true_guidance_scalenumber
0 to 10
1True classifier-free guidance scale passed to the pipeline.

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-edit-multiangle",
    "input": {
      "image": "<image>"
    }
  }'