Available now

Qwen Multiple Angles: new camera angles

By Alibaba

Qwen Multiple Angles shows the scene in your image from a new camera position: turned, moved closer, or seen from above or below.

Model ID
Maker
Alibaba

Input

Fields marked * are required. Review the price before generating.

The image to adjust camera angle for.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

If not provided, the size of the final input image will be used.

Additional settings

The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.

The number of inference steps to perform.

Acceleration level for image generation. 'regular' balances speed and quality.

Random seed for reproducibility. Same seed with same prompt will produce same result.

Rotate camera left (positive) or right (negative) in degrees. Positive values rotate left, negative values rotate right.

Move camera forward (0=no movement, 10=close-up)

Adjust vertical camera angle (-1=bird's-eye view/looking down, 0=neutral, 1=worm's-eye view/looking up)

Enable wide-angle lens effect

The scale factor for the LoRA model. Controls the strength of the camera control effect.

Price$0.06 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

Upload an image and move the camera with sliders. Rotate it up to 90° to the left or right, move it forward toward a close-up, and tilt between a bird's-eye view and a worm's-eye view. A wide-angle lens option widens the view.

There is no prompt. Make one to four images per run as PNG, JPEG or WebP.

What you can build

  • Extra product angles from one studio shot
  • Close-ups and wide views of the same scene
  • Low and high camera angles for a storyboard
  • Character views for reference sheets

Prompting tips

  • Move one control at a time to see what each one does to your image.
  • Small rotations keep more of the original; large ones invent more of the hidden side.
  • Lower the strength slider if the subject starts to change shape.

What to check

Inspect newly exposed surfaces and object geometry; this is a generated viewpoint, not a calibrated 3D reconstruction.

Inputs

  • Images (required): The URL of the image to adjust camera angle for.
  • Image Size (optional): The size of the generated image. If not provided, the size of the final input image will be used. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Guidance Scale (optional): The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. From 0 to 20.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 2 to 50.
  • Acceleration (optional): Acceleration level for image generation. 'regular' balances speed and quality. Options: none, regular.
  • Negative Prompt (optional): The negative prompt for the generation.
  • Seed (optional): Random seed for reproducibility. Same seed with same prompt will produce same result.
  • Output Format (optional): The format of the output image. Options: png, jpeg, webp.
  • Number of Images (optional): Number of images to generate. From 1 to 4.
  • Rotate Right-Left (degrees °) (optional): Rotate camera left (positive) or right (negative) in degrees. Positive values rotate left, negative values rotate right. From -90 to 90.
  • Move Forward → Close-Up (optional): Move camera forward (0=no movement, 10=close-up).
  • Vertical Angle (Bird ⬄ Worm) (optional): Adjust vertical camera angle (-1=bird's-eye view/looking down, 0=neutral, 1=worm's-eye view/looking up).
  • Wide-Angle Lens (optional): Enable wide-angle lens effect.
  • Lora Scale (optional): The scale factor for the LoRA model. Controls the strength of the camera control effect. From 0 to 4.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • File formats: PNG, JPEG, WEBP.
  • Up to 4 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 megapixel: $0.06 / megapixel