Vidu Text To Image Q2

Vidu Text To Image Q2

Playground

Vidu Text-to-Image Q2 converts text prompts into high-quality images with exceptional visual detail and creative flexibility. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

vidu/text-to-image-q2 — High-resolution cinematic text-to-image

vidu/text-to-image-q2 is a high-end text-to-image model that focuses on clean composition, cinematic lighting, and high resolutions up to 4K. It’s built for scenarios where a single image has to carry a lot of visual weight: posters, key visuals, thumbnails, or product hero shots.

Why it’s useful

• Cinematic aspect ratios – choose from 1:1, 16:9, 9:16, 4:3, 3:4, 21:9, 2:3, 3:2 for social posts, banners, and vertical feeds.
• High resolutions (1080p → 4K) – generate images ready for large displays, detailed crops, or light print use.
• Prompt-driven style control – supports rich, descriptive prompts for mood, camera angle, lens type, lighting, and composition.
• Consistent structure and detail – strong global coherence makes it suitable for scenes with multiple elements and clear storytelling.

How to use

1. prompt* – describe the scene, subject, mood, and style you want (for example: “cinematic nighttime city street, shallow depth of field, dramatic lighting, 35mm film look”).

2. aspect_ratio – pick the framing:

   • 1:1 for avatars, album covers, square posts
   • 16:9 / 21:9 for cinematic or banner shots
   • 9:16 for vertical / mobile content
   • 4:3, 3:4, 2:3, 3:2 for more traditional photography ratios

3. resolution – choose the output quality:

   • 1080p – fast preview and web-ready images
   • 2K – higher detail for close-ups and cropping
   • 4K – maximum sharpness and fidelity

4. Run the job, preview the result, and iterate on your prompt if needed.

Pricing

Tips for best results

• Use specific, photography-style language (lens type, lighting, time of day, camera angle) to get more cinematic images.
• Pair aspect_ratio with prompt hints like “widescreen establishing shot” or “vertical social ad portrait” to guide composition.
• For 4K images, write slightly richer prompts (background, textures, materials) so the extra resolution is filled with meaningful detail.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/text-to-image-q2" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "1:1",
    "resolution": "1080p",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"