Lovart logo

Lovart

Organization
okou-ai
lovart

Lovart API for AI-powered design generation. Use when user mentions "Lovart", "AI design", "generate image", "generate video", "AI art", "product photography", "marketing design", or visual content creation.

Overview

Publisherokou-ai
Repositoryokou-skills
Skill namelovart
Stars
81
Forks
19
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by okou-ai on GitHub. Read the source before you install it.

Installation

Install the Lovart AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/okou-ai/okou-skills/tree/main/lovart
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/okou-ai/okou-skills.git /tmp/okou-skills
mkdir -p .claude/skills
cp -r /tmp/okou-skills/lovart .claude/skills/lovart
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lovart in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lovart on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lovart is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Troubleshooting

If requests fail, run okou doctor check-connector --env-name LOVART_ACCESS_KEY or okou doctor check-connector --url https://lgw.lovart.ai/v1/openapi/mode/query --method POST

Authentication

All requests use AK/SK HMAC-SHA256 signature authentication. Each request requires five signed headers:

HeaderValue
X-Access-Key$LOVART_ACCESS_KEY
X-TimestampCurrent Unix timestamp
X-SignatureHMAC-SHA256 of {METHOD}\n{PATH}\n{TIMESTAMP} using $LOVART_SECRET_KEY
X-Signed-MethodHTTP method (e.g. POST)
X-Signed-PathRequest path (e.g. /v1/openapi/chat)

Environment Variables

VariableDescription
LOVART_ACCESS_KEYLovart access key (format: ak_...)
LOVART_SECRET_KEYLovart secret key (format: sk_...)

Key Endpoints

Base URL: https://lgw.lovart.ai

1. Generate Design (Chat)

POST /v1/openapi/chat

Send a natural-language prompt to generate images, videos, or other visual content. Returns a thread_id for tracking.

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "POST\n/v1/openapi/chat\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s -X POST "https://lgw.lovart.ai/v1/openapi/chat" --header "Content-Type: application/json" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: POST" --header "X-Signed-Path: /v1/openapi/chat" -d @/tmp/lovart_chat.json

Write to /tmp/lovart_chat.json:

json
{
  "prompt": "<your-design-description>",
  "project_id": "<your-project-id>"
}

To continue a conversation, add "thread_id": "<your-thread-id>".

To attach reference images, add "attachments": ["<cdn-url>"].

To specify a preferred model, add "tool_config": {"prefer_tool_categories": {"IMAGE": ["generate_image_flux_2_max"]}}.

To force a specific tool (e.g. upscale), add "tool_config": {"include_tools": ["upscale_image"]}.

Response: {"thread_id": "..."}

2. Check Generation Status

GET /v1/openapi/chat/status?thread_id=<thread-id>

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "GET\n/v1/openapi/chat/status\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s "https://lgw.lovart.ai/v1/openapi/chat/status?thread_id=<your-thread-id>" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: GET" --header "X-Signed-Path: /v1/openapi/chat/status"

Response includes status (running, done, pending_confirmation, failed) and progress (0-100).

3. Get Generation Result

GET /v1/openapi/chat/result?thread_id=<thread-id>

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "GET\n/v1/openapi/chat/result\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s "https://lgw.lovart.ai/v1/openapi/chat/result?thread_id=<your-thread-id>" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: GET" --header "X-Signed-Path: /v1/openapi/chat/result"

Response includes items with generated artifacts (image URLs, video URLs) and thread_id.

4. Confirm High-Cost Operation

POST /v1/openapi/chat/confirm

When status is pending_confirmation, confirm to proceed with high-cost operations (e.g. video generation).

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "POST\n/v1/openapi/chat/confirm\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s -X POST "https://lgw.lovart.ai/v1/openapi/chat/confirm" --header "Content-Type: application/json" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: POST" --header "X-Signed-Path: /v1/openapi/chat/confirm" -d @/tmp/lovart_confirm.json

Write to /tmp/lovart_confirm.json:

json
{
  "thread_id": "<your-thread-id>"
}

5. Create Project

POST /v1/openapi/project/save

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "POST\n/v1/openapi/project/save\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s -X POST "https://lgw.lovart.ai/v1/openapi/project/save" --header "Content-Type: application/json" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: POST" --header "X-Signed-Path: /v1/openapi/project/save" -d @/tmp/lovart_project.json

Write to /tmp/lovart_project.json:

json
{
  "project_id": "",
  "project_name": "<your-project-name>",
  "project_type": 3
}

Response includes project_id. Use the returned ID in subsequent chat requests.

6. Set Generation Mode

POST /v1/openapi/mode/set

Switch between fast mode (costs credits, no queue) and unlimited mode (free, may queue).

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "POST\n/v1/openapi/mode/set\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s -X POST "https://lgw.lovart.ai/v1/openapi/mode/set" --header "Content-Type: application/json" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: POST" --header "X-Signed-Path: /v1/openapi/mode/set" -d @/tmp/lovart_mode.json

For fast mode, write to /tmp/lovart_mode.json:

json
{
  "unlimited": false
}

For unlimited mode, write to /tmp/lovart_mode.json:

json
{
  "unlimited": true
}

7. Query Generation Mode

POST /v1/openapi/mode/query

bash
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "POST\n/v1/openapi/mode/query\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s -X POST "https://lgw.lovart.ai/v1/openapi/mode/query" --header "Content-Type: application/json" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: POST" --header "X-Signed-Path: /v1/openapi/mode/query" -d '{}'

Available Models

Use model names in tool_config.prefer_tool_categories or tool_config.include_tools:

IMAGE: generate_image_midjourney, generate_image_nano_banana_pro, generate_image_nano_banana_2, generate_image_nano_banana, generate_image_gpt_image_1_5, generate_image_seedream_v5, generate_image_seedream_v4_5, generate_image_seedream_v4, generate_image_imagen_v4, generate_image_flux_2_max, generate_image_flux_2_pro

VIDEO: generate_video_seedance_v2_0, generate_video_seedance_v2_0_fast, generate_video_seedance_pro_v1_5, generate_video_kling_v3, generate_video_kling_v3_omni, generate_video_kling_v2_6, generate_video_kling_omni_v1, generate_video_veo3_1, generate_video_veo3_1_fast, generate_video_veo3, generate_video_sora_v2_pro, generate_video_sora_v2, generate_video_wan_v2_6, generate_video_hailuo_v2_3, generate_video_vidu_q2

3D: generate_3d_tripo

UTILITY: upscale_image

Common Workflows

Generate an Image and Retrieve the Result

bash
# Step 1: Send chat request
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "POST\n/v1/openapi/chat\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s -X POST "https://lgw.lovart.ai/v1/openapi/chat" --header "Content-Type: application/json" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: POST" --header "X-Signed-Path: /v1/openapi/chat" -d '{"prompt": "A modern logo design with gradient blue to purple", "project_id": "<your-project-id>"}'

# Step 2: Poll status until done (replace <thread-id> from Step 1)
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "GET\n/v1/openapi/chat/status\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s "https://lgw.lovart.ai/v1/openapi/chat/status?thread_id=<your-thread-id>" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: GET" --header "X-Signed-Path: /v1/openapi/chat/status"

# Step 3: Get result when status is "done"
TIMESTAMP=$(date +%s) && SIGNATURE=$(echo -ne "GET\n/v1/openapi/chat/result\n${TIMESTAMP}" | openssl dgst -sha256 -hmac "$LOVART_SECRET_KEY" | awk '{print $NF}') && curl -s "https://lgw.lovart.ai/v1/openapi/chat/result?thread_id=<your-thread-id>" --header "X-Access-Key: $LOVART_ACCESS_KEY" --header "X-Timestamp: ${TIMESTAMP}" --header "X-Signature: ${SIGNATURE}" --header "X-Signed-Method: GET" --header "X-Signed-Path: /v1/openapi/chat/result"

Upscale an Image

Use include_tools to force the upscale tool:

Write to /tmp/lovart_chat.json:

json
{
  "prompt": "upscale this image to 4K",
  "project_id": "<your-project-id>",
  "attachments": ["<your-image-cdn-url>"],
  "tool_config": {
    "include_tools": ["upscale_image"]
  }
}

Guidelines

  1. Signature freshness: The HMAC signature includes a timestamp — recompute TIMESTAMP and SIGNATURE for every request, as the server rejects stale signatures
  2. Signed path must match: The X-Signed-Path header must exactly match the request path (without query string), e.g. /v1/openapi/chat not /v1/openapi/chat?thread_id=xxx
  3. Polling: Image generation typically takes 10-30s; video generation can take minutes — poll chat/status until status is done
  4. Pending confirmation: When status is pending_confirmation, call chat/confirm before the generation proceeds — do NOT auto-confirm, ask the user first as it may cost credits
  5. Thread reuse: Pass thread_id to continue a conversation — the Agent remembers prior context and can iterate on designs
  6. Project required: All chat requests need a project_id — create one with project/save first or reuse an existing one
  7. Mode affects cost: Fast mode (unlimited: false) uses credits for priority processing; unlimited mode (unlimited: true) is free but may queue

API Reference

Frequently asked questions

What does the Lovart AI skill do?

Lovart API for AI-powered design generation. Use when user mentions "Lovart", "AI design", "generate image", "generate video", "AI art", "product photography", "marketing design", or visual content creation.

Why use Lovart on TypingMind?

Because you install it once and use it with any model. Lovart is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lovart in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/okou-ai/okou-skills/tree/main/lovart. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Lovart?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lovart?

As many as you like. As long as a model supports skills, you can use Lovart with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lovart AI skill free?

It is published on GitHub by okou-ai. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇