Skip to content
Back to search

lovart-skill

a skill for lovart agent

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/lovartai/lovart-skill with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/lovartai/lovart-skill'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/lovartai-lovart-skill/badge.svg)](/listings/lovartai-lovart-skill)

HTML

<a href="/listings/lovartai-lovart-skill"><img src="/api/listings/lovartai-lovart-skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Choose the path that matches your agent ecosystem. **OpenClaw is the officially published distribution** (`npx skills add` pulls the latest release from ClawHub); **Hermes Agent is a manual install** you copy into your skills tree. Both paths install the same skill files; the difference is only in how the agent discovers and invokes them.

Set your credentials once either way — they are the same in both ecosystems:

export LOVART_ACCESS_KEY="ak_xxx"
export LOVART_SECRET_KEY="sk_xxx"

Get your AK/SK from the Lovart platform (Avatar menu -> AK/SK Management).

OpenClaw

npx skills add lovartai/lovart-skill

Pulls the latest published release from ClawHub. OpenClaw installs the skill into your project and auto-discovers it through its `metadata.openclaw` block.

Hermes Agent

Hermes Agent discovers skills from `~/.hermes/skills/<category>/<skill-name>/SKILL.md`. This is a **manual / community install** — there is no automated publish target in this repo yet.

git clone https://github.com/lovartai/lovart-skill.git
cd lovart-skill
cp -r skills/lovart-skill ~/.hermes/skills/design/lovart-api

Hermes auto-triggers on any visual / audio creation request through its `metadata.hermes.tags` block. From your Hermes chat:

/lovart-api draw a cyberpunk cat in neon city

> 💡 The two paths install identical skill files — the `SKILL.md` > ships dual-format frontmatter, so the same artifact serves both > ecosystems without modification.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 411 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <p align="center">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="assets/lovart-icon.svg" />
  4. <source media="(prefers-color-scheme: light)" srcset="assets/lovart-icon-dark.svg" />
  5. <img src="assets/lovart-icon-dark.svg" width="96" height="96" alt="Lovart" />
  6. </picture><br/>
  7. <strong>lovart-skill</strong><br/><br/>
  8. <a href="https://github.com/lovartai/lovart-skill/releases"><img src="https://img.shields.io/github/v/release/lovartai/lovart-skill" alt="Release" /></a>
  9. <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT" /></a>
  10. <a href="https://python.org"><img src="https://img.shields.io/badge/Python-3.6+-green.svg" alt="Python 3.6+" /></a><br/>
  11. <strong>English</strong> | <a href="README_CN.md">简体中文</a> | <a href="README_TW.md">繁體中文</a> | <a href="README_JA.md">日本語</a>
  12. </p>
  13. <br/>
  14. > Lovart AI Agent Skills — generate images, video, and audio from any
  15. > AI coding assistant. One `SKILL.md`, two install paths.
  16. ## ✨ What it does
  17. This skill connects your AI coding assistant to Lovart's Agent OpenAPI.
  18. It works with both the [OpenClaw](https://openclaw.com) and [Hermes Agent](https://github.com/l3ad3r1/Hermes-skills) ecosystems out of the box, and also runs from any assistant that can invoke Python scripts. Capabilities:
  19. - 🖼️ **Image generation** — posters, logos, illustrations, banners, mockups, etc.
  20. - 🎬 **Video generation** — clips, animations, product videos
  21. - 🎵 **Audio generation** — BGM, songs, sound effects
  22. - ✂️ **Image/video editing** — upscale, reframe, style transfer
  23. - 🧊 **3D generation** — 3D models from text or images
  24. - 📁 **Project & thread management** — multi-project support with local state persistence
  25. ## 📦 Install
  26. Choose the path that matches your agent ecosystem. **OpenClaw is the
  27. officially published distribution** (`npx skills add` pulls the
  28. latest release from ClawHub); **Hermes Agent is a manual install**
  29. you copy into your skills tree. Both paths install the same skill
  30. files; the difference is only in how the agent discovers and invokes
  31. them.
  32. Set your credentials once either way — they are the same in both
  33. ecosystems:
  34. ```bash
  35. export LOVART_ACCESS_KEY="ak_xxx"
  36. export LOVART_SECRET_KEY="sk_xxx"
  37. ```
  38. Get your AK/SK from the Lovart platform (Avatar menu -> AK/SK Management).
  39. ### OpenClaw
  40. ```bash
  41. npx skills add lovartai/lovart-skill
  42. ```
  43. Pulls the latest published release from ClawHub. OpenClaw installs
  44. the skill into your project and auto-discovers it through its
  45. `metadata.openclaw` block.
  46. ### Hermes Agent
  47. Hermes Agent discovers skills from `~/.hermes/skills/<category>/<skill-name>/SKILL.md`.
  48. This is a **manual / community install** — there is no automated
  49. publish target in this repo yet.
  50. ```bash
  51. git clone https://github.com/lovartai/lovart-skill.git
  52. cd lovart-skill
  53. cp -r skills/lovart-skill ~/.hermes/skills/design/lovart-api
  54. ```
  55. Hermes auto-triggers on any visual / audio creation request through
  56. its `metadata.hermes.tags` block. From your Hermes chat:
  57. ```
  58. /lovart-api draw a cyberpunk cat in neon city
  59. ```
  60. > 💡 The two paths install identical skill files — the `SKILL.md`
  61. > ships dual-format frontmatter, so the same artifact serves both
  62. > ecosystems without modification.
  63. ## 🚀 Quick start
  64. ```bash
  65. # Generate an image
  66. python3 scripts/agent_skill.py chat --prompt "a cyberpunk cat in neon city" --json --download
  67. # Generate a video
  68. python3 scripts/agent_skill.py chat --prompt "ocean waves crashing on rocks, cinematic" --json --download
  69. # Generate BGM
  70. python3 scripts/agent_skill.py chat --prompt "lofi hip-hop, chill, study vibes" --json --download
  71. ```
  72. ## 🛠️ Commands
  73. ### Generation
  74. | Command | Description |
  75. |---------|-------------|
  76. | `chat` | Send prompt, wait for completion, return all results at once. Main command. |
  77. | `watch` | Send prompt and stream artifacts as they complete (NDJSON, incremental delivery) |
  78. | `send` | Send prompt without waiting (returns thread_id immediately) |
  79. | `confirm` | Confirm a pending high-cost operation (e.g. video), then wait |
  80. | `result` | Get results for a thread |
  81. | `status` | Check thread status |
  82. ### Project management
  83. | Command | Description |
  84. |---------|-------------|
  85. | `projects` | List all projects |
  86. | `project-add` | Add and switch to a project |
  87. | `project-switch` | Switch active project (supports prefix match) |
  88. | `project-rename` | Rename a project |
  89. | `project-remove` | Remove a project and its threads |
  90. | `create-project` | Create a new empty project on the server |
  91. ### Configuration
  92. | Command | Description |
  93. |---------|-------------|
  94. | `config` | View/update local settings (`~/.lovart/state.json`) |
  95. | `threads` | List saved conversation threads |
  96. | `set-mode` | Switch between fast (credits) / unlimited (queue) mode |
  97. | `query-mode` | Check current generation mode |
  98. ### File operations
  99. | Command | Description |
  100. |---------|-------------|
  101. | `upload` | Upload a local file to CDN (returns URL) |
  102. | `upload-artifact` | Upload a URL artifact to a project |
  103. | `download` | Download artifacts from URLs |
  104. ## 💡 Usage examples
  105. ```bash
  106. # Use an existing project
  107. python3 scripts/agent_skill.py chat --project-id PROJECT_ID --prompt "draw a cat" --json --download
  108. # Continue a conversation (thread reuse preserves context)
  109. python3 scripts/agent_skill.py chat --thread-id THREAD_ID --prompt "make it blue" --json --download
  110. # Stream artifacts as they complete (NDJSON, for multi-image/video requests)
  111. python3 scripts/agent_skill.py watch --prompt "generate 4 variations of a cyberpunk cat"
  112. # Edit with reference image
  113. python3 scripts/agent_skill.py upload --file photo.jpg
  114. python3 scripts/agent_skill.py chat --prompt "change the style to watercolor" --attachments "CDN_URL" --json --download
  115. # Prefer a specific model
  116. python3 scripts/agent_skill.py chat --prompt "draw a cat" \
  117. --prefer-models '{"IMAGE":["generate_image_midjourney"]}' --json --download
  118. # Force a specific tool (e.g. upscale instead of re-generate)
  119. python3 scripts/agent_skill.py chat --prompt "upscale this image" \
  120. --include-tools upscale_image --attachments "IMAGE_URL" --json --download
  121. # Thinking mode — deep structured reasoning for complex requests
  122. python3 scripts/agent_skill.py chat --prompt "design a brand identity for a coffee startup" \
  123. --mode thinking --json --download
  124. # Project management
  125. python3 scripts/agent_skill.py projects
  126. python3 scripts/agent_skill.py project-add --project-id NEW_ID --name "My Brand Kit"
  127. python3 scripts/agent_skill.py project-switch --project-id NEW_ID
  128. python3 scripts/agent_skill.py threads
  129. ```
  130. ## 🎯 Model selection
  131. You can control which model the Agent uses in three ways:
  132. 1. **In the prompt** (simple) — `"generate ocean waves video using kling"`
  133. 2. **`--prefer-models`** (soft preference) — `'{"IMAGE":["generate_image_midjourney"]}'`
  134. 3. **`--include-tools`** (strongest steer, not an enforced whitelist) — `upscale_image`
  135. `--include-tools` is a strong instruction the Agent normally follows, but it may still pick
  136. another tool — for example after the requested one rejects the input. `--exclude-tools` is
  137. accepted for forward compatibility and currently has no effect on tool selection.
  138. ## 🖼️ Reference subjects
  139. `--attachments` takes any image URL and each new URL is reviewed again. For a reference that
  140. already lives in the asset library, pass its library URL with `--subjects` so the existing
  141. review is reused and the Agent knows the subject is approved:
  142. ```bash
  143. python3 scripts/agent_skill.py chat --prompt "put these characters in one scene" \
  144. --subjects '[{"url":"LIBRARY_URL","asset_id":"asset_xxx","display_name":"Hero"}]' \
  145. --json --download
  146. ```
  147. ## ⚠️ Rejected tool calls
  148. A run can finish `done` and still have had tool calls rejected — the Agent may drop a
  149. reference or switch models and carry on. The result carries a `failures` array plus a
  150. one-line `warning`. Read it before reporting success; retrying a rejected reference with the
  151. same input will fail again and still costs credits.
  152. Available models:
  153. | Category | Tool name | Display name | Premium |
  154. |---|---|---|---|
  155. | IMAGE | `generate_image_seedream_v5_5` | Seedream 5.5 | |
  156. | IMAGE | `generate_image_gpt_image_2_6_flare` | GPT Image 2.6 Flare Auto | |
  157. | IMAGE | `generate_image_gpt_image_2_6_flare_low` | GPT Image 2.6 Flare Low | |
  158. | IMAGE | `generate_image_gpt_image_2_6_flare_medium` | GPT Image 2.6 Flare Medium | |
  159. | IMAGE | `generate_image_gpt_image_2_6_flare_high` | GPT Image 2.6 Flare High | |
  160. | IMAGE | `generate_image_gpt_image_2_6_flare_xhigh` | GPT Image 2.6 Flare xhigh | |
  161. | IMAGE | `generate_image_gpt_image_2_6_flare_max` | GPT Image 2.6 Flare Max | |
  162. | IMAGE | `generate_image_gpt_image_2_6_sunburst` | GPT Image 2.6 Sunburst Auto | |
  163. | IMAGE | `generate_image_gpt_image_2_6_sunburst_low` | GPT Image 2.6 Sunburst Low | |
  164. | IMAGE | `generate_image_gpt_image_2_6_sunburst_medium` | GPT Image 2.6 Sunburst Medium | |
  165. | IMAGE | `generate_image_gpt_image_2_6_sunburst_high` | GPT Image 2.6 Sunburst High | |
  166. | IMAGE | `generate_image_gpt_image_2_6_sunburst_xhigh` | GPT Image 2.6 Sunburst xhigh | |
  167. | IMAGE | `generate_image_gpt_image_2_6_sunburst_max` | GPT Image 2.6 Sunburst Max | |
  168. | IMAGE | `generate_image_gpt_image_2_5_flare` | GPT Image 2.5 Flare Auto | |
  169. | IMAGE | `generate_image_gpt_image_2_5_flare_low` | GPT Image 2.5 Flare Low | |
  170. | IMAGE | `generate_image_gpt_image_2_5_flare_medium` | GPT Image 2.5 Flare Medium | |
  171. | IMAGE | `generate_image_gpt_image_2_5_flare_high` | GPT Image 2.5 Flare High | |
  172. | IMAGE | `generate_image_gpt_image_2_5_flare_xhigh` | GPT Image 2.5 Flare xhigh | |
  173. | IMAGE | `generate_image_gpt_image_2_5_flare_max` | GPT Image 2.5 Flare Max | |
  174. | IMAGE | `generate_image_gpt_image_2_5_sunburst` | GPT Image 2.5 Sunburst Auto | |
  175. | IMAGE | `generate_image_gpt_image_2_5_sunburst_low` | GPT Image 2.5 Sunburst Low | |
  176. | IMAGE | `generate_image_gpt_image_2_5_sunburst_medium` | GPT Image 2.5 Sunburst Medium | |
  177. | IMAGE | `generate_image_gpt_image_2_5_sunburst_high` | GPT Image 2.5 Sunburst High | |
  178. | IMAGE | `generate_image_gpt_image_2_5_sunburst_xhigh` | GPT Image 2.5 Sunburst xhigh | |
  179. | IMAGE | `generate_image_gpt_image_2_5_sunburst_max` | GPT Image 2.5 Sunburst Max | |
  180. | IMAGE | `generate_image_gpt_image_2` | GPT Image 2 Auto | |
  181. | IMAGE | `generate_image_gpt_image_2_low` | GPT Image 2 Low | |
  182. | IMAGE | `generate_image_gpt_image_2_medium` | GPT Image 2 Medium | |
  183. | IMAGE | `generate_image_gpt_image_2_high` | GPT Image 2 High | |
  184. | IMAGE | `generate_image_nano_banana_2_1` | Nano Banana 2.1 | |
  185. | IMAGE | `generate_image_nano_banana_pro` | Nano Banana Pro | |
  186. | IMAGE | `generate_image_nano_banana_2` | Nano Banana 2 | |
  187. | IMAGE | `generate_image_nano_banana_2_lite` | Nano Banana 2 Lite | |
  188. | IMAGE | `generate_image_seedream_v5_pro` | Seedream 5.0 Pro | |
  189. | IMAGE | `generate_image_seedream_v5` | Seedream 5.0 Lite | |
  190. | IMAGE | `generate_image_seedream_v4_5` | Seedream 4.5 | |
  191. | IMAGE | `generate_image_seedream_v4` | Seedream 4 | |
  192. | IMAGE | `generate_image_minimax_h3` | MiniMax H3 Image | |
  193. | IMAGE | `generate_image_minimax_h3_highspeed` | Minimax h3 highspeed | ⭐ Premium |
  194. | IMAGE | `generate_image_kling_v4` | Kling Image 4.0 | |
  195. | IMAGE | `generate_image_qwen_image3` | Qwen Image3 | |
  196. | IMAGE | `generate_image_qwen_image3_pro` | Qwen Image3 Pro | |
  197. | IMAGE | `generate_image_gpt_image_1_5` | GPT Image 1.5 | |
  198. | IMAGE | `generate_image_luma_uni_1` | Luma uni-1 | |
  199. | IMAGE | `generate_image_luma_uni_1_max` | Luma uni-1-max | |
  200. | IMAGE | `generate_image_flux_2_max` | Flux.2 Max | |
  201. | IMAGE | `generate_image_flux_2_pro` | Flux.2 Pro | |
  202. | IMAGE | `generate_image_midjourney` | Midjourney | |
  203. | IMAGE | `generate_image_ideogram_v4` | Ideogram 4 | |
  204. | IMAGE | `generate_image_p_image_ideogram` | Ideogram P-Image | |
  205. | VIDEO | `generate_video_seedance_v2_5` | Seedance 2.5 | ⭐ Premium |
  206. | VIDEO | `generate_video_seedance_v2_5_flash` | Seedance 2.5 Flash | ⭐ Premium |
  207. | VIDEO | `generate_video_seedance_v2_0` | Seedance 2.0 | ⭐ Premium |
  208. | VIDEO | `generate_video_seedance_v2_0_fast` | Seedance 2.0 Fast | ⭐ Premium |
  209. | VIDEO | `generate_video_seedance_v2_0_mini` | Seedance 2.0 Mini | ⭐ Premium |
  210. | VIDEO | `generate_video_wan_v3` | Wan 3.0 | ⭐ Premium |
  211. | VIDEO | `generate_video_wan_v3_prime` | Wan 3.0 Prime | ⭐ Premium |
  212. | VIDEO | `generate_video_minimax_h3` | MiniMax H3 | ⭐ Premium |
  213. | VIDEO | `generate_video_minimax_h3_max` | MiniMax H3 Max | ⭐ Premium |
  214. | VIDEO | `generate_video_kling_v4` | Kling 4.0 | ⭐ Premium |
  215. | VIDEO | `generate_video_kling_v4_flash` | Kling 4.0 Flash | ⭐ Premium |
  216. | VIDEO | `generate_video_kling_v3` | Kling 3.0 | ⭐ Premium |
  217. | VIDEO | `generate_video_kling_v3_omni` | Kling 3.0 Omni | ⭐ Premium |
  218. | VIDEO | `generate_video_kling_v2_6` | Kling 2.6 | ⭐ Premium |
  219. | VIDEO | `generate_video_kling_omni_v1` | Kling O1 | ⭐ Premium |
  220. | VIDEO | `generate_video_wan_v2_6` | Wan 2.6 | |
  221. | VIDEO | `generate_video_hailuo_v2_3` | Hailuo 2.3 | |
  222. | VIDEO | `generate_video_vidu_q2` | Vidu Q2 | |
  223. | VIDEO | `generate_video_gemini_omni_flash` | Gemini Omni Flash | ⭐ Premium |
  224. ## 🧠 Reasoning modes
  225. Control how the agent thinks per request via `--mode`:
  226. - **`fast`** (default) — lightweight single-pass response. Faster, cheaper, suitable for simple one-shot generations.
  227. - **`thinking`** — deep structured reasoning with planning and multi-step analysis. Use for complex brand systems, multi-asset campaigns, anything that benefits from deliberate planning. Slower but higher quality.
  228. ```bash
  229. # Quick, single-shot (default)
  230. python3 scripts/agent_skill.py chat --prompt "draw a cat"
  231. # Deliberate, plan-first reasoning
  232. python3 scripts/agent_skill.py chat --prompt "design a full brand identity" --mode thinking
  233. ```
  234. **Mode is locked to the thread on its first message.** To switch modes, start a new thread (omit `--thread-id`). Mirrors the Lovart web UI toggle.
  235. ## ⚡ Billing modes
  236. Separate from reasoning mode. This is a persistent account-level billing setting:
  237. ```bash
  238. # Fast — costs credits, no queue
  239. python3 scripts/agent_skill.py set-mode --fast
  240. # Unlimited — free, may queue
  241. python3 scripts/agent_skill.py set-mode --unlimited
  242. # Check current
  243. python3 scripts/agent_skill.py query-mode
  244. ```
  245. ## 🚦 Rate limits
  246. The API enforces per-account request frequency limits, split into two tiers based on the endpoint you hit:
  247. | Tier | Endpoints | Per minute | Per hour |
  248. |------|-----------|-----------|---------|
  249. | **Chat** (write) | `/chat`, `/chat/confirm` | 60 | 600 |
  250. | **Query** (read) | `/chat/status`, `/chat/result`, `/project/*`, `/mode/*`, everything else | 300 | 3000 |
  251. The stricter `Chat` tier protects generation. The `Query` tier is much looser so polling for status/results doesn't eat into your generation budget.
  252. Exceeding a limit returns `HTTP 429` with `Retry-After: 60`.
  253. This is separate from **generation concurrency** — each thread can only run one generation task at a time. If a task is already running in a thread, new requests to that thread are rejected with `HTTP 409` until it finishes. You can run tasks in different threads concurrently.
  254. The skill auto-retries on transient network errors (3 attempts with backoff), but rate limit and billing errors are returned immediately.
  255. ## 💾 Local state
  256. Settings and thread history are persisted at `~/.lovart/state.json`:
  257. ```json
  258. {
  259. "active_project": "abc123...",
  260. "projects": {
  261. "abc123...": {"name": "My Project", "created_at": "..."}
  262. },
  263. "threads": [
  264. {"id": "xxx", "project_id": "abc123...", "topic": "cyberpunk cat", "updated_at": "..."}
  265. ]
  266. }
  267. ```
  268. ## 🤖 Integration
  269. The skill works with multiple agent ecosystems. Pick the one that
  270. matches yours.
  271. ### OpenClaw
  272. ```bash
  273. npx skills add lovartai/lovart-skill
  274. ```
  275. OpenClaw reads `metadata.openclaw` from `SKILL.md` and auto-discovers
  276. the skill after install — no extra configuration beyond the env vars.
  277. ### Hermes Agent
  278. Drop the skill into `~/.hermes/skills/<category>/<skill-name>/` (see
  279. the Hermes subsection under `Install` above). Hermes reads
  280. `metadata.hermes` and routes visual / audio creation requests to the
  281. skill via its `/lovart-api` slash command.
  282. ### Other AI assistants
  283. The skill also works with Claude Code, Cursor, and any assistant that
  284. can invoke Python scripts directly. See `SKILL.md` for the full
  285. integration contract.
  286. ## 📁 Project structure
  287. ```
  288. lovart-skill/
  289. ├── README.md
  290. ├── README_CN.md
  291. ├── README_TW.md
  292. ├── README_JA.md
  293. └── skills/
  294. └── lovart-skill/
  295. ├── SKILL.md # Skill contract (dual-format: OpenClaw + Hermes)
  296. └── scripts/
  297. └── agent_skill.py # Python client (zero dependencies)
  298. ```
  299. ## 🔒 Security & privacy
  300. - **Local state file**: The skill reads/writes `~/.lovart/state.json` to persist your active project and recent thread IDs. No other files are accessed.
  301. - **Outbound calls**: Only talks to the Lovart API (`https://lgw.lovart.ai`) and Lovart CDN (for downloading your own generated artifacts). No third-party services.
  302. - **API keys**: AK/SK are read from env vars (`LOVART_ACCESS_KEY` / `LOVART_SECRET_KEY`) and signed with HMAC-SHA256 per request. Keys are never logged or persisted to disk.
  303. - **TLS**: SSL certificate verification is **enabled by default**. Set `LOVART_INSECURE_SSL=1` to disable (only if you're behind a corporate proxy/VPN that intercepts TLS).
  304. - **Source code**: `skills/lovart-skill/scripts/agent_skill.py` is ~900 lines of pure Python standard library — you're encouraged to read it before installing.
  305. ## 🏗️ Architecture
  306. ```
  307. OpenClaw / Hermes Agent / Claude Code / other AI assistant
  308. -> scripts/agent_skill.py (this skill)
  309. -> Lovart OpenAPI (AK/SK HMAC-SHA256 auth)
  310. -> Lovart AI Agent (model selection, orchestration)
  311. -> Generated images / videos / audio
  312. ```
  313. ## 🤝 Contributing
  314. Contributions are welcome! Feel free to:
  315. - [Open an issue](https://github.com/lovartai/lovart-skill/issues) to report bugs or suggest features
  316. - [Submit a pull request](https://github.com/lovartai/lovart-skill/pulls) to fix issues or add improvements
  317. ## 📄 License
  318. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.