Qwen Image 3
Qwen · AI imageQwen Image 3 is Qwen's unified image generation and editing model, served on VidMachine through OpenRouter's dedicated Images API. It produces high-quality images from text prompts and supports image-to-image editing with up to 4 reference images, making it a strong fit for scene stills, start frames, and continuity workflows.
The model supports 1K and 2K resolution tiers with a wide range of aspect ratios including vertical 9:16 for short-form video.
Key features and benefits
Quality and style
Qwen Image 3 targets strong photorealism and flexible artistic output from natural-language prompts. It handles detailed scenes, accurate text rendering, and consistent multi-image generation for story-driven shorts.
Aspect ratios
Supported aspect ratios include 1:1, 1:2, 1:4, 2:1, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 9:16, and 16:9. VidMachine defaults to 9:16 for shorts and start frames so generated assets align with vertical delivery formats.
Reference images
When your project or scene pipeline provides reference URLs—such as a project hero image or the previous segment's starting frame—VidMachine sends up to 4 references so the model can use visual context alongside your text prompt.
OpenRouter routing
On VidMachine this model runs only through OpenRouter's dedicated Images API (POST /api/v1/images), not Replicate. You need OPENROUTER_API_KEY configured in the environment; billing uses VidMachine credits per image.
Technical specifications
ProviderQwen (Alibaba Cloud Int.)
OpenRouter modelqwen/qwen-image-3
Aspect ratios1:1, 1:2, 1:4, 2:1, 2:3, 3:2, 3:4, 4:1, 4:3, 4:5, 5:4, 9:16, 16:9
Resolution1K, 2K
Reference imagesUp to 4
VidMachine routingOpenRouter Images API (POST /api/v1/images)
Use cases and applications
Qwen Image 3 suits automated shorts pipelines—starting frames for AI Video, full scene stills for AI Images, and cover-style assets when paired with your prompt workflow.
Use it when you want a unified text-to-image and image-to-image model on OpenRouter with portrait aspect support and reference-image continuity.
Why this model
Choose Qwen Image 3 for Qwen-backed image generation with portrait aspect support, up to 4 reference images, and 1K–2K resolution—integrated on VidMachine at a fixed credit cost through OpenRouter's Images API.
How VidMachine uses it
Internal model id: qwen-image-3. Generation uses OpenRouter POST /api/v1/images with aspect_ratio (default 9:16) and resolution 1K.
Reference images from the project and previous segment frames are attached as input_references when available, matching other image models in the pipeline.
Billed at 7 credits per generated image.
What you should know
Does Qwen Image 3 run on Replicate in VidMachine?
No. This model is OpenRouter-only on VidMachine. Select qwen-image-3 in image_model_priority and ensure OPENROUTER_API_KEY is set.
Which aspect ratio should I use for Shorts?
VidMachine uses 9:16 by default for scene and start-frame generation, which Qwen Image 3 supports natively.