Available now

Qwen Face to Full Portrait: portrait from a face

By Alibaba

Qwen Face to Full Portrait turns a cropped close-up of a face into a wider portrait of the same person, dressed and placed as you describe.

Model ID
Maker
Alibaba

Input

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

The cropped face image. Provide a close-up face photo.

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.

Describe the full portrait you want to generate from the face. Include clothing, setting, pose, and style details.

Example prompt. Edit it or write your own.

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.

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

Price$0.06 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

Upload a close-up face photo and describe the portrait around it: clothing, setting, pose and style. Without a prompt you get a professional portrait in natural light. Each run returns up to four images in square, portrait or landscape sizes.

A LoRA scale sets how strongly the portrait effect shapes the result; the default of 1 suits most photos.

What you can build

  • Team or profile portraits from cropped headshots
  • Full-length character images from a face reference
  • The same face shown in several outfits and settings

Prompting tips

  • Use a sharp, front-facing crop with even light; the face carries over from it.
  • Name clothing, place and framing in the prompt, such as "waist-up, navy suit, office window behind".
  • Pick a portrait size when you want the body in frame.

What to check

Compare facial likeness, neck and clothing boundaries with the reference; the added body and scene are generated.

Inputs

  • Images (required): The URL of the cropped face image. Provide a close-up face photo.
  • 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.
  • Prompt (optional): Describe the full portrait you want to generate from the face. Include clothing, setting, pose, and style details.
  • Lora Scale (optional): The scale factor for the LoRA model. Controls the strength of the LoRA 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