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.

Restyles one portrait as a neon-lit night scene in one of six looks, from a convenience store aisle to a pool after dark or a club full of green lasers.

Places whoever is in your portrait at a smoky studio table with a gold trophy made of toy bricks, for World Cup 2026 posts. Returns a short clip, a still, or both.

Stable Audio 3 Small SFX by Stability AI generates stereo sound effects from text prompts, up to 120 seconds, for games, video, and product UX.

Create up to 2 minutes of stereo music from a text description with Stable Audio 3 Small Music by Stability AI. Control duration, steps, and guidance.

Stable Audio 3 Medium by Stability AI generates stereo music from text prompts for up to 380 seconds. Control duration, steps, guidance, and output format. ([fal.ai](https://fal.ai/models/fal-ai/stable-audio-3/medium/text-to-audio/api))

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.

Cosmos 3 Super turns a reference image and motion prompt into a physics-grounded MP4 clip, with controls for aspect ratio, FPS, audio, and safety.

Football fan clips for eight national teams, where the subject cheers with pom-poms in the team's colours, plus golden-goal and trophy scenes in men's and women's versions.

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.

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.

Sulphur 2 Base by SulphurAI is an LTX 2.3 fine-tune for text-to-video and image-to-video. Create short MP4 clips with first and last frame control.

Restyles one portrait as an LGBTQ+ themed fashion shoot and animates it. The 38 looks include rainbow-flag Pride scenes and a long series of black-and-white studio editorials.

Transform images into trending TikTok effects with customizable styles and durations. Apply various creative filters to create engaging video content.

Pixal3D converts a single image into a textured 3D GLB mesh. It uses pixel-to-3D back-projection so geometry stays aligned to the input view.

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.

SenseNova U1-8B turns text into high-detail images with strong layout control and clearer in-image text. Use it for posters, infographics, and concept art.