Search the full model catalog.

LocateAnything 3B by Nvidia localizes objects, UI elements, and text in images. It returns normalized boxes or points from natural-language prompts.

Extend an existing clip with PixVerse Video Extend V6. Upload a short MP4 or MOV, describe the continuation, and get a longer MP4 in 360p–1080p.

Stable Audio 3 Medium is the mid-size open-weight text-to-music model in Stability AI's Stable Audio 3 family. It also makes solo instrument stems and sound effects, in clips up to 6 minutes 20 seconds.

Type a team name and the person in your portrait shows up in that country's kit across five World Cup 2026 scenes, from the tunnel walk to a goal celebration.

Horror-movie scenes in which a figure in a white mask and black hooded robe waits near the person from your photo, in five everyday settings such as a phone call in bed.

OpenMOSS MOSS-TTS v1.5 turns text into natural speech, with optional zero-shot voice cloning from a reference clip. It supports 31 languages plus pause and pronunciation control.

Microsoft's 3.8B-parameter text-to-image model, pre-trained on 800 million image-text pairs with long GPT-4.1 captions. It renders at a 1440 or 1024 base size in nine aspect ratios from 1:2 to 2:1.

Turn a detailed scene description into a short video clip. Lance Text to Video can also animate a still image or rewrite an existing video.

Create short videos from a still image plus a motion prompt. Grok Imagine Video 1.5 by xAI outputs 480p or 720p MP4 clips with synced audio.

Influencer-style fashion shoots built from a single selfie, with small movements added. Its 43 presets cover white studio sets, an office look, motorcycle scenes and a poolside villa.

u1-8b-interleave by SenseNova generates step-by-step text with matching images, optionally conditioned on up to 5 reference images. It suits tutorials, diaries, and infographics.

Google’s Lyria 3 generates a 30-second, 48 kHz stereo music clip from a detailed description, with an optional image to guide mood and style.

Pruna’s WAN T2V generates a short MP4 video from a detailed scene prompt. Pick 480p or 720p, choose 16:9 or 9:16, and control motion and safety options.

Tencent HunyuanVideo-1.5-i2v animates one reference image into a prompt-guided video clip with coherent motion, 480p–1080p presets, and reproducible seeds.

Tencent’s HunyuanVideo 1.5 T2V turns detailed prompts into MP4 video clips with coherent motion. Control resolution, aspect ratio, frames, steps, and seed.

Puts the person from a portrait in the middle of a fight: kaiju battles, wuxia duels, mecha brawls and boss-style entrances. Eight of the 92 scenes can cast a second real person as the opponent.

Multilingual text-to-speech from OpenBMB: 2B parameters, 30 languages, 48 kHz output. Clone a voice from a short clip or describe a new one in words, with audio streamed back as it is generated.

Snap your fingers and the world around you freezes in a cinematic time-stop video made from one portrait. 63 scenarios across street magic, bullet-time action, fantasy, supernatural, sports and weddings.

Generate 2-10s videos in 720p or 1080p from reference images or a short clip. Wan 2.7 R2V keeps subject identity while following your prompt.

Multilingual speech-to-text for 25 European languages with auto language detection, punctuation, capitalization, and optional timestamps.