wavespeedGenerate and edit images and videos using WaveSpeed AI's 700+ model library. Use when the user wants to generate images from text prompts (FLUX, Seedream, Qw...
Install via ClawdBot CLI:
clawdbot install al1enjesus/wavespeed700+ AI models (Google, OpenAI, ByteDance, Kling, Luma) via one API. Images in <2s, videos in <2min.
WAVESPEED_API_KEY env var — already set in all Clawster containers, just use it directlyTOOLS.md in the workspace — look for WaveSpeed AI sectionNever search for the key — if WAVESPEED_API_KEY is in the environment, it's ready to go. Check with:
echo $WAVESPEED_API_KEYSign up at wavespeed.ai → Dashboard → API Keys.
New accounts get free credits. Pay-as-you-go pricing — no subscription required.
export WAVESPEED_API_KEY=your_key_hereThe skill script is at skills/wavespeed/scripts/wavespeed.js.
# Image generation
node wavespeed.js generate --model flux --prompt "sunset over mountains" --output out.png
node wavespeed.js generate --model seedream --prompt "..." --size 1024x1024
# Image editing (face/portrait-safe — preserves identity)
node wavespeed.js edit --model nbp --prompt "change bathrobe to black hoodie, dark background" \
--image https://example.com/photo.jpg --output result.png
# Video from image
node wavespeed.js video --model wan-i2v --prompt "slow cinematic zoom" \
--image https://example.com/frame.jpg --output clip.mp4
# List all aliases
node wavespeed.js models
# Check task status
node wavespeed.js status --id task_abc123| Task | Alias | Best for |
|------|-------|---------|
| Edit photo keeping face | nbp | Portrait retouching, outfit/bg change |
| Fast image gen | flux-schnell | Drafts, quick tests |
| Best image quality | flux-pro / seedream | Final outputs |
| Image → Video | wan-i2v | Fast, affordable |
| Premium video | kling / veo | Cinematic quality |
| Text → Video | sora / veo | Story videos |
See references/models.md for full model list with IDs, params, and pricing.
nbp, nb-edit): always pass images as images: [url] array — this is requiredgoogle/nano-banana-pro/edit is the best model for editing photos while keeping the person's face identical--output to specify path--images url1,url2Generated Mar 1, 2026
Online retailers can generate high-quality product images from text descriptions, such as 'luxury watch on marble table', using models like flux-pro or seedream for final outputs. They can also edit existing product photos to change backgrounds or outfits with nbp, keeping models' faces identical while showcasing different styles.
Content creators and marketers can quickly generate images from prompts for posts or ads using fast models like flux-schnell for drafts. They can animate photos into videos with wan-i2v for engaging reels or upscale videos to 4K for higher quality on platforms like YouTube and Instagram.
Photographers and studios can retouch portraits by changing clothes or backgrounds with nbp, preserving facial identity for professional headshots or creative projects. This allows for efficient editing without reshoots, saving time and resources in post-production workflows.
Filmmakers and animators can generate videos from text prompts using premium models like kling or veo for cinematic quality, or from images with wan-i2v for faster turnaround. This supports storyboarding, short film creation, and enhancing existing footage with AI-driven effects.
Advertising agencies can create and edit visual assets for campaigns, such as generating images from text for concept art or editing photos to swap outfits for targeted demographics. Using models like sora for text-to-video enables dynamic ad content that captures audience attention across digital channels.
Charge users based on API calls for image generation, editing, or video creation, with tiered pricing per task (e.g., per image or minute of video). This model leverages the 700+ model library, offering flexibility for clients to scale usage without subscriptions, attracting small businesses and developers.
Provide free credits to new users upon sign-up, encouraging trial and adoption, then monetize through top-ups or premium features like faster processing or access to high-end models like flux-pro. This model builds user engagement and converts free users to paying customers over time.
Offer customized API integrations or branded interfaces for large companies in industries like retail or media, allowing them to embed WaveSpeed AI into their own products. This model generates revenue through licensing fees, long-term contracts, and support services tailored to enterprise needs.
💬 Integration Tip
Ensure the WAVESPEED_API_KEY environment variable is set and accessible in your container, and use the provided script commands directly for tasks like image generation or editing to avoid configuration issues.
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Capture frames or clips from RTSP/ONVIF cameras.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
Generate images using the internal Google Antigravity API (Gemini 3 Pro Image). High quality, native generation without browser automation.
使用内置 image_generate.py 脚本生成图片, 准备清晰具体的 `prompt`。
AI image generation powered by CellCog. Create images, edit photos, consistent characters, product photography, reference-based images, sets of images, style transfer. Professional image creation with AI.