Premiumgoogle/nano-banana-2
Google Image generation with conversational editing, multi-image fusion and character consistency.
Ouvrir le modèleGenerate Images, Vidéo, captions, voices, Musique and Chat from a dedicated studio with saved results and plan-aware limits.
Texte and reference-image models for Premium visual creation.
PremiumGoogle Image generation with conversational editing, multi-image fusion and character consistency.
Ouvrir le modèle
PremiumOpenAI Image generation and editing with strong instruction following and sharp Texte rendering.
Ouvrir le modèle
PremiumBytedance Seedream 4.5 Image generation with stronger spatial understanding and world knowledge.
Ouvrir le modèle
PremiumxAI Image generation for expressive, high-detail creative scenes.
Ouvrir le modèle
PremiumFast Imagen 4 generation when speed and cost matter.
Ouvrir le modèleAnime generation and anime-style Image transformation models.
Créer custom emoji-style assets from short prompts.
Restore old photos, damaged Images and faces with AI repair models.
Restore damaged photos, repair scratches and colorize old Images while preserving the original subject.
Ouvrir le modèlePractical face restoration for old photos and AI-generated faces with cleaner facial detail.
Ouvrir le modèleCréer textured 3D assets and downloadable model Fichiers from prompts or reference Images.
Generate textured 3D model assets from detailed prompts with strong geometry and material fidelity.
Ouvrir le modèleGenerate 3D assets from a reference Image with texture, mesh and Gaussian PLY export options.
Ouvrir le modèlePrompt-vers-video and reference-video generation models.
PremiumGenerate videos using xAI Grok Imagine Vidéo.
Ouvrir le modèle
PremiumSeedance Lite text-vers-video and image-vers-video generation.
Ouvrir le modèle
PremiumVeo 3.1 Vidéo generation with reference Image support and higher-fidelity output.
Ouvrir le modèle
PremiumOpenAI Sora 2 Pro synced-audio Vidéo generation.
Ouvrir le modèle
PremiumA fast optimized Wan 2.2 text-vers-video model.
Ouvrir le modèleAlibaba Happy Horse turns prompts or a reference Image into cinematic HD Vidéo clips with duration and aspect controls.
Ouvrir le modèleCréer a talking avatar Vidéo from one portrait Image, a script, selected Voix and language.
Ouvrir le modèleSwap a source face into a target Vidéo clip with a dedicated Vidéo face-swap workflow.
Ouvrir le modèleFace-aware Image editing, reference and identity-preserving Image models.
Super-resolution and crisp Image enhancement models.
Full songs, instrumentals and Audio generation models.
Voix synthesis and Voix cloning models.
PremiumInworld realtime text-vers-speech with preset voices.
Ouvrir le modèle
PremiumMiniMax low-latency multilingual text-vers-audio with emotion control.
Ouvrir le modèle
PremiumKokoro 82M text-vers-speech based on StyleTTS2.
Ouvrir le modèle
PremiumCoqui XTTS-v2 multilingual text-vers-speech Voix cloning.
Ouvrir le modèleVidéo understanding, transcript and caption generation models.
Chat, coding, reasoning and multimodal language models.
PremiumGoogle Gemini 3.1 Pro for reasoning, research and high-quality Chat.
Ouvrir le modèle
PremiumOpenAI GPT-5.2 for coding, agentic work, reasoning and multimodal tasks.
Ouvrir le modèle
PremiumGoogle Gemini 3 Pro advanced reasoning with multimodal input support.
Ouvrir le modèle
PremiumDeepSeek V3.1 hybrid thinking model for coding and technical work.
Ouvrir le modèle
PremiumQwen3 large instruction model for writing, planning and structured answers.
Ouvrir le modèle