mirror of
https://github.com/hanzoui/workflow-templates-broken-zap-2026-06-08.git
synced 2026-10-30 20:44:35 +00:00
1.5 KiB
1.5 KiB
WaveSpeed
WaveSpeed is a high-performance AI inference platform providing accelerated access to 700+ models for image, video, audio, and text generation via unified REST APIs.
Model Variants
WaveSpeed Image Models
- FLUX family (dev, schnell, pro) with sub-2-second generation
- Seedream, Ideogram, Z-Image, and Qwen-Image integrations
WaveSpeed Video Models
- WAN 2.x, Kling, Veo, Seedance, PixVerse, and LTX-2 19B access
WaveSpeed Audio Models
- ACE-Step 1.5 for music generation in 50+ languages
- Inworld 1.5 text-to-speech with 56+ multilingual voices
Key Features
- Ultra-fast inference: images in under 2 seconds, video in under 2 minutes
- Unified API access to 700+ curated, production-ready models
- Pay-as-you-go credits starting at ~$0.006 per image
- Exclusive access to ByteDance Seedream V3, Kling, and Alibaba WAN
Hardware Requirements
- Cloud API platform with no local hardware required
- RESTful API with SDKs for Python, JavaScript, and other languages
- Web UI (Studio) and desktop app available for interactive use
Common Use Cases
- Rapid prototyping and bulk content generation
- Developer integration for AI-powered media applications
- High-volume marketing and e-commerce asset creation
- Video upscaling and enhancement pipelines
Key Parameters
- model: specific model identifier (e.g., wavespeed-ai/z-image/turbo)
- prompt: text description for generation
- resolution: output dimensions
- num_images: batch generation count