Premiumgoogle/nano-banana-2
Google Hoto generation with conversational editing, multi-image fusion and character consistency.
Open modelGenerate Hotuna, Bidiyo, captions, voices, Kiɗa and Hira from a dedicated studio with saved results and plan-aware limits.
Rubutu and reference-image models for Premium visual creation.
PremiumGoogle Hoto generation with conversational editing, multi-image fusion and character consistency.
Open model
PremiumOpenAI Hoto generation and editing with strong instruction following and sharp Rubutu rendering.
Open model
PremiumBytedance Seedream 4.5 Hoto generation with stronger spatial understanding and world knowledge.
Open model
PremiumxAI Hoto generation for expressive, high-detail creative scenes.
Open model
PremiumFast Imagen 4 generation when speed and cost matter.
Open modelAnime generation and anime-style Hoto transformation models.
Ƙirƙira custom emoji-style assets from short prompts.
Restore old photos, damaged Hotuna and faces with AI repair models.
Restore damaged photos, repair scratches and colorize old Hotuna while preserving the original subject.
Open modelPractical face restoration for old photos and AI-generated faces with cleaner facial detail.
Open modelƘirƙira textured 3D assets and downloadable model Fayiloli from prompts or reference Hotuna.
Prompt-zuwa-video and reference-video generation models.
PremiumGenerate videos using xAI Grok Imagine Bidiyo.
Open model
PremiumSeedance Lite text-zuwa-video and image-zuwa-video generation.
Open model
PremiumVeo 3.1 Bidiyo generation with reference Hoto support and higher-fidelity output.
Open model
PremiumOpenAI Sora 2 Pro synced-audio Bidiyo generation.
Open model
PremiumA fast optimized Wan 2.2 text-zuwa-video model.
Open modelAlibaba Happy Horse turns prompts or a reference Hoto into cinematic HD Bidiyo clips with duration and aspect controls.
Open modelƘirƙira a talking avatar Bidiyo from one portrait Hoto, a script, selected Murya and language.
Open modelSwap a source face into a target Bidiyo clip with a dedicated Bidiyo face-swap workflow.
Open modelFace-aware Hoto editing, reference and identity-preserving Hoto models.
Super-resolution and crisp Hoto enhancement models.
Full songs, instrumentals and Sauti generation models.
Murya synthesis and Murya cloning models.
PremiumInworld realtime text-zuwa-speech with preset voices.
Open model
PremiumMiniMax low-latency multilingual text-zuwa-audio with emotion control.
Open model
PremiumKokoro 82M text-zuwa-speech based on StyleTTS2.
Open model
PremiumCoqui XTTS-v2 multilingual text-zuwa-speech Murya cloning.
Open modelBidiyo understanding, transcript and caption generation models.
Hira, coding, reasoning and multimodal language models.
PremiumGoogle Gemini 3.1 Pro for reasoning, research and high-quality Hira.
Open model
PremiumOpenAI GPT-5.2 for coding, agentic work, reasoning and multimodal tasks.
Open model
PremiumGoogle Gemini 3 Pro advanced reasoning with multimodal input support.
Open model
PremiumDeepSeek V3.1 hybrid thinking model for coding and technical work.
Open model
PremiumQwen3 large instruction model for writing, planning and structured answers.
Open model