The AI Playground

Black Forest Labs' flagship image model. Generates photorealistic, high-detail images in just 4 steps with exceptional quality.

Meta's most powerful open-source LLM. Chat with the frontier open model rivaling GPT-4 across reasoning, coding, and creative tasks.

World-class open-source coding model that beats GPT-4o on coding benchmarks. Supports 338 programming languages.

Ultra-fast image generation with Stable Diffusion XL Turbo. Generate photorealistic images in under 1 second from text prompts.

Meta's Segment Anything Model 2. Click on any object in an image and SAM instantly creates a precise mask.

Fast, efficient open-source LLM that outperforms much larger models. Ideal for edge deployment and cost-sensitive applications.

Google's open-weight Gemma 2 model. Excellent multilingual reasoning, math, and coding with Apache 2.0 license.

Meta's AI music generation model. Create high-quality music from text descriptions or condition on a melody input.

Precise image generation control with poses, depth maps, canny edges, and more. The professional creative control tool for Stable Diffusion.

Microsoft's compact multimodal model. Understands images and answers complex questions with impressive efficiency.

State-of-the-art speech recognition by OpenAI. Transcribe audio in 99 languages with incredible accuracy and timestamps.

Highly realistic text-to-speech by Suno AI with emotion, laughter, music, and sound effects. The most expressive open TTS model available.