AI Model Playground
Explore and experiment with our collection of AI models for video, image, and audio generation.
Parameters and models shown here may be inaccurate — this playground is for testing only. Always refer to the official documentation for up-to-date information.
Showing all 76 models
Video Generation
28 models
Veo 3.1
Google's newest video model. Fast and Quality modes with text-to-video and image-to-video support.
SeeDance 2.0 Pro
ByteDance
ByteDance's highest quality video model with omni-reference, first & last frame, and T2V at 720p.
Kling 3.0
Kling
Latest Kling model with multi-shot support, 3-15s duration, and sound generation.
Grok Imagine Video
xAI
xAI video generation with 6-15 second durations at 480p-720p. Text and image-to-video support.
Kling O1
Kling
Kling's reasoning model for complex prompts. Superior understanding and creative interpretation.
MiniMax Hailuo
MiniMax
Flexible video generation with motion control. Customizable duration and resolution options.
Kling 2.5 Turbo
Kling
Fast Kling model optimized for speed. 5s and 10s durations with multiple aspect ratios.
Kling 2.1
Kling
Stable Kling model with professional and standard quality tiers. Reliable results.
Kling 2.1 Master
Kling
Premium Kling model for highest quality output. Best for professional productions.
Higgsfield
Higgsfield
Cinematic videos with 50+ camera effects. Dolly shots, zooms, and drone perspectives.
Kling 2.6 Motion Control
Kling
Transfer motion from a reference video onto a character image. Perfect for dance and movement replication.
Kling 3.0 Motion Control
Kling
Transfer motion from reference videos onto characters with high facial consistency. Upgraded from v2.6.
Higgsfield Cinematic Studio Video
Higgsfield
Professional cinematic videos with camera movements. AI sound effects and slow motion support.
Kling 2.6
Kling
Latest Kling model with enhanced dynamics and aesthetics. Supports text-to-video and image-to-video.
SeeDance 2.0 Fast
ByteDance
Fast video generation with omni-reference, first & last frame, and T2V at 720p.
SeeDance 1.5 Pro
ByteDance
Professional videos with first & last frame support at 720p/1080p, 5-12 seconds.
Wan 2.6
Alibaba
Wan AI's latest model with extended 15s duration, multi-shot, and audio support.
SeeDance 1.0 Pro
ByteDance
Text-to-video and first & last frame at 720p with 5-10 second duration.
Wan 2.5
Alibaba
Wan AI video generation with text-to-video and image-to-video capabilities.
SeeDance 1.0 Mini
ByteDance
Lightweight model with multi-frame keypoint control at 720p/1080p.
Wan 2.6 Flash
Alibaba
Faster, cheaper variant of Wan 2.6 with T2V, I2V, and R2V support.
SeeDance 1.0 Fast
ByteDance
Fast generation with multi-frame support at 720p/1080p.
Wan 2.2
Alibaba
Wan AI with advanced frame and quality step control for precise output.
Wan 2.2 Fast
Alibaba
Quick Wan 2.2 video generation with auto-calculated frames.
Topaz Video Upscale
Topaz Labs
AI video upscaling to 4K with frame interpolation, slow motion, and enhancement presets.
Kling 3.0 Omni
Kling
Kling 3.0 Omni image-to-video with sound support. 5-10s at 720p-1080p.
Kling 3.0 Omni Edit
Kling
AI video editing with Kling 3.0 Omni. Edit videos using text prompts and reference images.
Kling O1 Edit
Kling
Reasoning-powered video editing. Transform videos with complex edit instructions and reference images.
Image Generation
30 modelsWan 2.7 Image Pro
Alibaba
Highest quality AI images with thinking mode, up to 4K resolution, and editing with up to 9 references.
Nano Banana 2
Next-generation Google Gemini image model with up to 4K resolution and reference image support.
Flux.2
Black Forest Labs
Black Forest Labs image model. Supports 3 modes: Flex, Pro, and Max with reference images.
Grok Imagine Image
xAI
xAI image generation and editing with up to 5 reference images. Supports text-to-image and edit modes.
Nano Banana Pro
Gemini 3 Preview with 1K/2K/4K resolution control. Advanced image generation capabilities.
Nano Banana
Google's Gemini 2.5 Flash image model. Fast, high-quality image generation and editing.
Higgsfield Cinematic Studio Image
Higgsfield
Cinematic images with professional camera settings. Adjustable lens, aperture, and focal length.
GPT Image 1.5
OpenAI
Enhanced OpenAI image model with improved quality. Better detail and prompt adherence.
GPT Image 1
OpenAI
OpenAI's photorealistic model. Excellent text rendering and complex prompt understanding.
Flux.2 Klein 9B
Black Forest Labs
Lightweight Flux.2 model for fast image generation at $0.0105/MP.
Flux.2 Klein 4B
Black Forest Labs
Smallest and fastest Flux.2 model for rapid image generation at $0.0098/MP.
SeeDream 4.6
ByteDance
ByteDance AI image generation with up to 6 reference images and 4K resolution.
SeeDream 4.0
ByteDance
ByteDance AI image generation with up to 8 reference images support.
SeeDream 4.1
ByteDance
ByteDance AI image generation with up to 6 reference images and 4K resolution.
SeeDream 4.5
ByteDance
Enhanced ByteDance model with 14 reference images and 4K resolution.
SeeDream 5.0 Lite
ByteDance
ByteDance lightweight image model with 14 reference images and 3K resolution.
Kling O1 Image
Kling
High-quality AI images with 10 reference images and 9 aspect ratio options.
Kling 3.0 Omni Image
Kling
AI images with auto aspect ratio, 4K resolution, and element support. 10 reference inputs.
Topaz Image Upscale
Topaz Labs
AI image upscaling up to 16x with face enhancement and optimized presets for photos, text, and anime.
Qwen Image 2.0 Pro
Alibaba
Alibaba's highest quality image model with text rendering, image editing, and multi-image fusion.
Qwen Image 2.0
Alibaba
Faster accelerated version of 2.0 Pro with image editing support at lower cost.
Qwen Image Max
Alibaba
Photorealistic images with fewest AI artifacts. Text-to-image and image editing (specialized edit model).
Qwen Image Plus
Alibaba
Diverse artistic styles with fast generation. Text-to-image and image editing (specialized edit model).
Qwen Image
Alibaba
Alibaba's base image model with text-to-image and image editing support.
Z-Image Turbo
Alibaba
Lightweight fast text-to-image model with Chinese and English text rendering.
Wan 2.7 Image
Alibaba
Fast AI image generation with thinking mode and editing support. Max 2K resolution.
Wan 2.6 Image
Alibaba
AI image generation with style transfer and editing using 1-4 reference images.
Wan 2.5 Image
Alibaba
AI image generation with editing support using 1-3 reference images.
Wan 2.2 Image
Alibaba
Text-to-image only AI image generation with negative prompt support.
Wan 2.2 Image Flash
Alibaba
Fastest and cheapest Wan image model. Text-to-image only.
Audio Generation
18 models
Suno Music
Suno
Create original songs with vocals and instrumentation. Simple and custom modes available.
Suno Extend
Suno
Extend existing songs or uploaded audio. Continue from any timestamp.
Suno Cover
Suno
Generate cover versions in different styles. Transform existing songs.
Suno Add Vocals
Suno
Add AI vocals to uploaded music. Custom lyrics and timing control.
Suno Add Instrumental
Suno
Add instrumental backing to uploaded audio. Multiple styles available.
Suno Extract Stems
Suno
Extract vocals, drums, bass, guitar and more from any song.
Suno Lyrics
Suno
Generate song lyrics from descriptions. Returns two variations to choose from.
Suno WAV Export
Suno
Export Suno AI clips as high-quality WAV audio files.
Suno Extract All Stems
Suno
Extract all stems from a song — vocals, backing vocals, drums, bass, guitar, keyboard, and more.
Suno Sound Effects
Suno
Generate sound effects from text descriptions. Supports one-shot and loop modes with BPM and key control.
Higgsfield TTS
Higgsfield
Text-to-speech with customizable voices. Adjustable speed, style, and stability.
Suno Voice Creation
Suno
Create custom voices from audio recordings with verification. Use in music generation.
Suno Custom Model
Suno
Train a custom audio model from 6-24 of your own tracks. Use the trained model for music generation.
ElevenLabs TTS
ElevenLabs
High-quality text-to-speech with multiple voice options and models.
ElevenLabs Dialogue
ElevenLabs
Multi-voice dialogue generation for conversations with multiple speakers.
ElevenLabs Sound Effects
ElevenLabs
AI sound effect generation from text descriptions with variable duration and loop support.
ElevenLabs Audio Isolation
ElevenLabs
AI-powered vocal isolation to separate vocals from instrumentals.
ElevenLabs Speech-to-Text
ElevenLabs
Audio transcription with event tagging, subtitle support, and custom key terms.