AI Models Directory

Google's fast conversational image generation and editing model.

Pro-tier Nano Banana with 4K output, Thinking mode and search grounding.

Google's cinematic video model with native audio generation.

OpenAI's natively multimodal image generation model.

OpenAI's video model with synchronized dialogue and sound.

OpenAI's steerable text-to-speech voices.

Midjourney's flagship image model, loved for its aesthetics.

The FLUX family: strong prompt adherence and typography.

ByteDance's high-fidelity bilingual image model.

ByteDance's multi-shot video generation model.

Kuaishou's Kling 2: high-dynamics realistic video generation.

MiniMax's Hailuo video model with strong physics.

MiniMax's multilingual voice synthesis model.

Runway's Gen-4: consistent characters and world-building.

Alibaba's Wan video model with audio-visual sync.

Suno's v5: full songs with vocals from a text prompt.

Udio's music model for studio-quality tracks.

ElevenLabs' most expressive text-to-speech model.