Nucleus Image Text To Image

Nucleus Image Text To Image

Playground

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.

Features

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

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.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "num_images": 1,
  "num_inference_steps": 50,
  "guidance_scale": 8,
  "output_format": "png"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/nucleus-image/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters