Seedance 2.0 is live! Start creating in Video Generator→
Se connecter
Accueil/Explorer/wavespeed-ai/nucleus-image/text-to-image

Nucleus Image

wavespeed-ai /

Nucleus Image generates high-quality images from text prompts with flexible aspect ratios, adjustable inference steps, and classifier-free guidance. Supports negative prompts, reproducible seeds, and multiple output formats. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-image
Input
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

A young woman in a beige trench coat sits by the window of a nearly empty subway car at 11:47 PM, cradling a bouquet of white baby's breath that's begun to wilt. A faded lipstick print stains the rim of her half-finished coffee cup; her eyes gaze blankly at the tunnel lights streaking past. At the far end of the car, a man in black-framed glasses watches her quietly — a concert ticket slipping from between his fingers. Cold white fluorescent ceiling light, faint fog condensation on the window glass, subtle reflections, 35mm film grain, Kodak Portra 400 aesthetic, cinematic 2.39:1 widescreen.

Votre requête coûtera $0.01 par exécution.

Pour $1 vous pouvez exécuter ce modèle environ 100 fois.

Encore une chose :

ExemplesTout voir

A young woman in a beige trench coat sits by the window of a nearly empty subway car at 11:47 PM, cradling a bouquet of white baby's breath that's begun to wilt. A faded lipstick print stains the rim of her half-finished coffee cup; her eyes gaze blankly at the tunnel lights streaking past. At the far end of the car, a man in black-framed glasses watches her quietly — a concert ticket slipping from between his fingers. Cold white fluorescent ceiling light, faint fog condensation on the window glass, subtle reflections, 35mm film grain, Kodak Portra 400 aesthetic, cinematic 2.39:1 widescreen.
A Martian base greenhouse, 2089. An American female botanist in her 40s kneels on the soil, staring through her helmet visor at the first sunflower ever grown on another planet. Rust-red Martian dust clings to her white spacesuit sleeves; her name tag reads "Dr. Lin." Outside the greenhouse dome: an orange Martian horizon with two small moons rising. In her other hand, she grips a folded, well-worn family photograph. Grounded sci-fi realism, soft diffused light, emotional contrast between warmth and desolation.

README

Nucleus Image Text-to-Image

Nucleus Image Text-to-Image generates high-quality images from text prompts with precise control over inference steps, guidance scale, and aspect ratio. An affordable, flexible text-to-image model built for creative and production workflows.

Why Choose This?

  • Fine-grained generation control Adjust inference steps (1–100) and guidance scale (0–20) to tune the balance between creativity and prompt adherence.

  • Negative prompt support Specify what to exclude from the output for more precise control over the result.

  • Multiple aspect ratio presets Choose from 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, or 2:3 to match any platform or format.

  • Batch generation Generate up to 2 images per run for quick side-by-side comparison.

  • Reproducible results Use the seed parameter to lock in a specific output for consistent iteration.

  • Output format choice Export in PNG or JPEG based on your delivery requirements.

Parameters

ParameterRequiredDescription
promptYesText description of the image subject, style, and mood.
negative_promptNoElements to exclude from the generated image.
aspect_ratioNoOutput aspect ratio. Options: 1:1 (default), 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.
num_imagesNoNumber of images to generate per run: 1 (default) or 2.
num_inference_stepsNoNumber of inference steps. Range: 1–100. Default: 50.
guidance_scaleNoClassifier-free guidance scale. Range: 0–20. Default: 8.
output_formatNoOutput file format: png (default) or jpeg.
seedNoRandom seed for reproducible results.

How to Use

  1. Write your prompt — describe the subject, scene, style, lighting, and mood.
  2. Add negative prompt (optional) — specify elements you want to exclude.
  3. Select aspect ratio — choose the format that fits your target platform.
  4. Set num_images (optional) — generate 1 or 2 images per run.
  5. Adjust inference steps and guidance scale (optional) — higher steps for more detail, higher guidance for stricter prompt adherence.
  6. Choose output format — png for lossless, jpeg for smaller file size.
  7. Set seed (optional) — fix the seed to reproduce a specific result.
  8. Submit — generate and download your image.

Pricing

Just $0.01 per image.

Best Use Cases

  • Rapid prototyping — Generate visual concepts quickly at very low cost for iteration and ideation.
  • Social media content — Create platform-optimized images across multiple aspect ratios.
  • High-volume workflows — Affordable per-image pricing makes it ideal for large-scale generation pipelines.
  • Creative exploration — Tune inference steps and guidance scale to explore different visual styles from the same prompt.
  • Developer integrations — Embed flexible, low-cost image generation into any app or workflow.

Pro Tips

  • Higher num_inference_steps (50–100) produces more detailed and refined results; lower values (10–20) are faster for quick drafts.
  • Increase guidance_scale for stricter prompt adherence; lower values allow more creative variation.
  • Use negative_prompt to avoid common artifacts like blurry faces, extra limbs, or unwanted styles.
  • Generate 2 images per run to quickly compare variations before committing to a final render.
  • Fix the seed while adjusting other parameters to isolate the effect of each change.

Notes

  • Only prompt is required; all other parameters are optional.
  • Maximum 2 images per generation run.
  • Please ensure your content complies with WaveSpeed AI's usage policies.