Moss Image Text To Image API Documentation

Moss Image Text To Image API Documentation

Playground

MOSS Image Text-to-Image generates images from long text prompts, with sharp Chinese and English text rendering, 1K or 2K output and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MOSS Image Text-to-Image generates images from detailed text prompts with strong support for Chinese and English text rendering. Describe the subject, composition, environment, lighting, and any text you want to appear, then choose the resolution and aspect ratio for the final image.

Why Choose This?

• Detailed prompt understanding — Use rich scene descriptions to control composition, subject, background, lighting, and visual style.
• Chinese and English text rendering — Create posters, signs, packaging, infographics, and other text-heavy visuals.
• 1K and 2K output — Choose 1k or 2k depending on your quality requirements.
• 15 aspect ratios — Generate images for a wide range of layouts and placements.
• Multiple output formats — Export as jpeg, png, or webp.

Parameters

How to Use

1. Write a prompt — Describe the subject, composition, background, lighting, and visual style. Put any text you want rendered in quotation marks.
2. Choose a resolution — Select 1k or 2k.
3. Choose an aspect ratio optional — Select the framing that fits your target layout.
4. Choose an output format optional — Use jpeg, png, or webp.
5. Set a seed optional — Use a fixed seed for repeatable results or -1 for random generation.
6. Submit — Generate and retrieve the finished image.

Pricing

Aspect ratio, output format, and seed do not add separate charges.

Best Use Cases

• Posters and promotional graphics — Generate visuals with Chinese or English text.
• Packaging concepts — Create product packaging and label designs.
• Infographics — Combine visual elements with readable text.
• Advertising creatives — Produce campaign and marketing concepts.
• Editorial imagery — Generate detailed compositions for publishing and social content.
• Creative image generation — Explore illustrations, photography, and stylized concepts from long-form prompts.

Pro Tips

• Describe the subject, composition, environment, lighting, and style clearly.
• Put text that should appear in the image inside quotation marks.
• Use detailed prompts when precise scene structure matters.
• Choose 2k when higher output detail is needed.
• Use a fixed seed when comparing prompt or parameter changes.

Notes

• prompt is required.
• resolution defaults to 1k.
• aspect_ratio defaults to 1:1.
• output_format defaults to jpeg.
• Use seed=-1 for random seed selection.
• Both Chinese and English text can be included in prompts and rendered in generated images.

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",
  "resolution": "1k",
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/moss-image/text-to-image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters