菜单
Generate, edit, and upscale images; create videos from images via Venice AI. Supports text-to-image, image-to-video (Sora, WAN), upscaling, and AI editing.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill venice-ai-media命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
| name | venice-ai-media |
| description | Generate, edit, and upscale images; create videos from images via Venice AI. Supports text-to-image, image-to-video (Sora, WAN), upscaling, and AI editing. |
| homepage | https://venice.ai |
| metadata | {"clawdbot":{"emoji":"🎨","requires":{"bins":["python3"],"env":["VENICE_API_KEY"]},"primaryEnv":"VENICE_API_KEY","notes":"Requires Python 3.10+","install":[{"id":"python-brew","kind":"brew","formula":"python","bins":["python3"],"label":"Install Python (brew)"}]}} |
Generate images and videos using Venice AI APIs. Venice is an uncensored AI platform with competitive pricing.
brew install python or system Python)vn_...)Option A: Environment variable
export VENICE_API_KEY="vn_your_key_here"
Option B: Clawdbot config (recommended - persists across sessions)
Add to ~/.clawdbot/clawdbot.json:
{
skills: {
entries: {
"venice-ai-media": {
env: {
VENICE_API_KEY: "vn_your_key_here",
},
},
},
},
}
python3 {baseDir}/scripts/venice-image.py --list-models
If you see a list of models, you're ready!
| Feature | Cost |
|---|---|
| Image generation | ~$0.01-0.03 per image |
| Image upscale | ~$0.02-0.04 |
| Image edit | $0.04 |
| Video (WAN) | ~$0.10-0.50 depending on duration |
| Video (Sora) | ~$0.50-2.00 depending on duration |
Use --quote with video commands to check pricing before generation.
# Generate an image
python3 {baseDir}/scripts/venice-image.py --prompt "a serene canal in Venice at sunset"
# Upscale an image
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 2
# Edit an image with AI
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "add sunglasses"
# Create a video from an image
python3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt "gentle camera pan" --duration 5s
python3 {baseDir}/scripts/venice-image.py --prompt "a serene canal in Venice at sunset"
python3 {baseDir}/scripts/venice-image.py --prompt "cyberpunk city" --count 4
python3 {baseDir}/scripts/venice-image.py --prompt "portrait" --width 768 --height 1024
python3 {baseDir}/scripts/venice-image.py --prompt "abstract art" --out-dir /tmp/venice
python3 {baseDir}/scripts/venice-image.py --list-models
python3 {baseDir}/scripts/venice-image.py --list-styles
python3 {baseDir}/scripts/venice-image.py --prompt "fantasy" --model flux-2-pro --no-validate
python3 {baseDir}/scripts/venice-image.py --prompt "photo" --style-preset "Cinematic" --embed-exif
Key flags: --prompt, --model (default: flux-2-max), --count (uses efficient batch API for same prompt), --width, --height, --format (webp/png/jpeg), --resolution (1K/2K/4K), --aspect-ratio, --negative-prompt, --style-preset (use --list-styles to see options), --cfg-scale (prompt adherence 0-20, default 7.5), --seed (for reproducible results), --safe-mode (disabled by default for uncensored output), --hide-watermark (only use if explicitly requested - watermark supports Venice), --embed-exif (embed prompt in image metadata), --lora-strength (0-100 for applicable models), --steps (inference steps, model-dependent), --enable-web-search, --no-validate (skip model check for new/beta models)
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 2
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --scale 4 --enhance
python3 {baseDir}/scripts/venice-upscale.py photo.jpg --enhance --enhance-prompt "sharpen details"
python3 {baseDir}/scripts/venice-upscale.py --url "https://example.com/image.jpg" --scale 2
Key flags: --scale (1-4, default: 2), --enhance (AI enhancement), --enhance-prompt, --enhance-creativity (0.0-1.0), --replication (0.0-1.0, preserves lines/noise, default: 0.35), --url (use URL instead of local file), --output, --out-dir
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "add sunglasses"
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "change the sky to sunset"
python3 {baseDir}/scripts/venice-edit.py photo.jpg --prompt "remove the person in background"
python3 {baseDir}/scripts/venice-edit.py --url "https://example.com/image.jpg" --prompt "colorize"
Key flags: --prompt (required - AI interprets what to modify), --url (use URL instead of local file), --output, --out-dir
Note: The edit endpoint uses the Qwen-Image model which has some content restrictions (unlike other Venice endpoints).
# Get price quote first (no generation)
python3 {baseDir}/scripts/venice-video.py --quote --model wan-2.6-image-to-video --duration 10s --resolution 720p
# Image-to-video (WAN 2.6 - default)
python3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt "camera pans slowly" --duration 10s
# Image-to-video (Sora)
python3 {baseDir}/scripts/venice-video.py --image photo.jpg --prompt "cinematic" \
--model sora-2-image-to-video --duration 8s --aspect-ratio 16:9 --skip-audio-param
# List models (shows available durations per model)
python3 {baseDir}/scripts/venice-video.py --list-models
# Clean up a video downloaded with --no-delete
python3 {baseDir}/scripts/venice-video.py --complete <queue_id> --model <model>
Key flags: --image (required for generation), --prompt (required for generation), --model (default: wan-2.6-image-to-video), --duration (model-dependent, see --list-models), --resolution (480p/720p/1080p), --aspect-ratio, --audio/--no-audio, --skip-audio-param, --quote (price estimate), --timeout, --poll-interval, --no-delete (keep server media), --complete (cleanup previously downloaded video), --no-validate (skip model check)
Progress: During generation, the script shows estimated progress based on Venice's average execution time.
Use --list-models to see current availability and status. Models change frequently.
Image: Default is flux-2-max. Common options include flux, gpt-image, and nano-banana variants.
Video:
--aspect-ratio, use --skip-audio-paramTips:
--no-validate for new or beta models not yet in the model list--quote for video to check pricing before generationScripts print a MEDIA: /path/to/file line for Clawdbot auto-attach.
Tip: Use --out-dir /tmp/venice-$(date +%s) when generating media to send via iMessage (ensures accessibility across user accounts).
"VENICE_API_KEY not set"
~/.clawdbot/clawdbot.jsonexport VENICE_API_KEY="vn_...""Invalid API key"
vn_"Model not found"
--list-models to see available models--no-validate for new/beta modelsVideo stuck/timeout
--timeout 600 for longer videos"requests" module not found
pip3 install requests
基于 SOC 职业分类