P H3 Image Text To Image LoRA API Documentation

P H3 Image Text To Image LoRA API Documentation

Playground

P-H3-Image by Pruna AI, built on MiniMax H3 open weights, generates photorealistic, editorial-quality images from text prompts with support for custom LoRA guidance, making it suitable for creative visuals, branded content, product imagery, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

P-H3-Image Text-to-Image LoRA generates images from text prompts using the MiniMax H3 open weights, with support for up to 3 custom LoRA weights per request. Create photorealistic, editorial, cinematic, and creative visuals from 1k up to 4k while applying custom styles, characters, products, or other LoRA-trained concepts.

Why Choose This?

• LoRA support — Load up to 3 LoRA weights in one request, each with its own scale.
• High-quality image generation — Create detailed images from natural-language descriptions.
• Up to 4K output — Choose 1k, 1.5k, 2k, 3k, or 4k.
• Flexible framing — Generate landscape, portrait, square, and ultrawide images.
• Multiple output formats — Export as JPEG, PNG, or WebP.
• Seed control — Use a fixed seed for more reproducible generation.

Parameters

How to Use

1. Write a prompt — Describe the subject, setting, composition, lighting, and visual style.
2. Add LoRAs optional — Load up to 3 LoRA weights and configure their scales.
3. Choose framing — Select the aspect ratio that fits your target layout.
4. Choose resolution — Select 1k through 4k depending on the required detail.
5. Choose output format optional — Select JPEG, PNG, or WebP.
6. Set a seed optional — Use a fixed seed when comparing prompt or LoRA changes.
7. Submit — Generate and retrieve the finished image.

Pricing

Pricing is based on the selected resolution and includes a fixed $0.015 LoRA surcharge per generation.

The LoRA surcharge is fixed per generation and does not increase with the number of LoRAs used within the supported limit.

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

Best Use Cases

• Custom styles — Apply LoRA-trained visual styles to generated images.
• Character generation — Generate characters guided by custom LoRA weights.
• Product imagery — Use LoRAs to guide specific products or visual identities.
• Advertising creatives — Produce customized campaign and promotional visuals.
• Editorial imagery — Create detailed photography and illustration concepts.
• High-resolution assets — Generate final images up to 4k.

Pro Tips

• Describe the subject, composition, lighting, environment, and visual style clearly.
• Adjust each LoRA scale based on how strongly you want it to influence the result.
• When combining multiple LoRAs, keep the prompt clear about the role of each concept.
• Use 3k or 4k when finer visual detail is important.
• Use a fixed seed when comparing prompt or LoRA changes.
• Put short text that should appear in the image inside quotation marks.

Notes

• prompt is required.
• Up to 3 LoRA weights can be used in one request.
• Each LoRA uses a {path, scale} configuration.
• aspect_ratio defaults to 1:1.
• resolution defaults to 1k.
• output_format defaults to jpeg.
• Use seed=-1 for random seed selection.
• Higher resolutions increase the base generation price.
• LoRA support adds a fixed $0.015 per generation.

Related Models

• P-H3-Image Text-to-Image — Generate images directly from text prompts.
• P-H3-Image Edit — Edit existing images with P-H3-Image.
• P-H3-Image Edit LoRA — Edit images with custom LoRA guidance.
• MiniMax H3 Text-to-Video — Generate videos with the MiniMax H3 model family.

Reference

• How to train your LoRA?
• How to use your LoRA?

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/p-h3-image/text-to-image-lora" \
  -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

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters