Model Catalog

MiniMax Video-01 turns text prompts into cinematic 720p clips in seconds, with smooth motion and dynamic camera work. No filming or editing skills needed.

MiniMax Video-01-Live is a text-to-video generation model that creates high-quality MP4 video clips with built-in prompt optimization for improved visual coherence and motion fidelity.

MiniMax Hailuo-2.3 Pro is an advanced text-to-video generation model that creates high-quality 1080p video with strong prompt understanding, cinematic motion, and support for detailed action and audio-aware prompts.

PixVerse v5 is a high-quality text-to-video generation model that creates video clips from text prompts, with support for multiple resolutions including 360p, 540p, 720p, and 1080p.

Smallest and fastest GPT-5 model optimized for low-cost text generation and lightweight tasks.

Google's Gemini 2.5 Flash: a fast, cost-efficient model for chat, writing, and everyday AI tasks.

A speed-tuned variant of Stable Diffusion XL that generates high-quality images in a handful of steps, trading a little fine detail for near-instant results - ideal for rapid concept exploration and draft iteration.

Alibaba's fast-inference Qwen Image variant, tuned for near-instant text-to-image generation without sacrificing prompt accuracy - built for rapid drafts and high-volume workflows.

Alibaba's Qwen Image model generates accurate, detailed visuals from text prompts with strong prompt comprehension, including legible in-image text and complex compositions.

Reads a depth map from your reference image to preserve spatial structure and perspective while regenerating textures, lighting, and style - ideal for reskinning a scene without losing its geometry.

Reads edge detection (Canny) from your reference image to lock in outlines and composition while the AI fills in new textures, colors, and detail - useful for restyling a piece while keeping its structure exact.

Preview aging like never before

Refines structure, lighting, and fine detail in an existing image while preserving its original composition - useful for cleaning up rough generations or enhancing a photo without changing what's in it.

Microsoft's compact vision-language model for dense image captioning, object detection, and visual grounding - reads an image and returns structured, accurate descriptions of what it contains.

A FLUX variant tuned by Krea for stylized, painterly image generation - strong for concept art and creative visuals that want more artistic flair than strict photorealism.

Turn audio and video into accurate, timestamped text in 99 languages. Run Fun AI studio Whisper in your browser no installs, no code

Image editing model . Can be able to handle 1-10 images single time with more accuracy in editing.

SAM 3D enables full scene reconstructions, placing objects and humans in a shared context together.

Convert a textured 3D model into a multicolor model suited for multicolor 3D printing with Hi3D.