Kwaivgi Kling Image O1 API Documentation

Kwaivgi Kling Image O1 API Documentation

Playground

Kling Omni Image O1 is Kuaishou’s multi-modal image generation model with MVL technology. Supports up to 10 reference images for feature consistency, precise detail editing (add/remove/modify), style control, and series content creation. Perfect for IP character design, comic panels, and brand merchandise. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Features

Kling Omni Image O1 is Kuaishou’s advanced multi-modal image generation model, featuring MVL (Multi-modal Visual Language) technology that combines natural language with image references for unprecedented creative control.

🌟 Four Key Advantages

1. Feature Consistency

Maintains subject characteristics across multiple images:

• Preserved outlines and core elements
• Consistent color tones and lighting
• Unified style across series

2. Precise Detail Modifications

Edit images without professional skills:

• Add new elements naturally
• Remove unwanted objects cleanly
• Modify specific details precisely
• Maintain original style and texture

3. Style Control

Apply and maintain artistic styles:

• Consistent visual language
• Brand-aligned aesthetics
• Cross-image style coherence

4. Rich Imagination

Generate creative variations while preserving identity:

• New poses and scenarios
• Environmental changes
• Creative interpretations

🎯 Use Cases

• IP Character Design — Create consistent character series
• Comic Panel Creation — Maintain character identity across panels
• Brand Merchandise — Unified styling for product lines
• Image Editing — Professional modifications without skills
• Series Content — Cohesive visual storytelling

🎬 Core Features

• Multi-Reference Support — Up to 10 reference images simultaneously
• Feature Extraction — Intelligent understanding of subject characteristics
• Cross-Image Consistency — Stable identity across generations
• Natural Language Control — Guide creation with text prompts

🚀 How to Use

1. Upload Reference Images Provide 1-10 reference images of your subject.

2. Describe Your Intent Write a prompt for the desired output. > Example: “The character in a winter coat, standing in a snowy forest, same art style”

3. Set Parameters Choose resolution and output format.

4. Generate Receive images with consistent subject features.

💡 Pro Tips

• Use multiple angles of the same subject for better feature extraction
• Provide clear, high-resolution reference images
• Specify style elements you want to maintain
• For character series, include various expressions and poses in references

Price

• $0.028 per run

📝 Example Workflows

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",
  "num_images": 1
}
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/kwaivgi/kling-image-o1" \
  -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