Search the full model catalog.

Bend fire, ice, wind, lightning, time and earth in cinematic VFX shorts generated from a single portrait. 13 scenarios.

Stage your portrait as a stylized dance or musical performance video. 25 scenarios across global cultures and stage styles.

Cinematic comedy reveals, twists and pet-life micro-dramas generated from a single portrait photo. 18 scenarios.

Defy gravity in cinematic levitation and zero-gravity videos generated from a single portrait photo. 12 scenarios.

Restyle your portrait into anime, manga, watercolor ink and cel-animation short films. 48 scenarios across action, romance, fantasy and stylized art.

Turn a single portrait photo into a stylized 3D animated short film with cinematic comedy timing and family-film CG aesthetics. 17 scenarios.

Qwen3.6-27B is a 27B dense vision-language model from Qwen for agentic coding and reasoning, with optional thinking traces in outputs. On Wiro a request takes about 25K input tokens and returns up to 16K.

A real-time, multilingual text-to-speech system offering expressive voice design and high-fidelity voice cloning through low-latency streaming inference.

Generate or edit images with GPT Image 2 from OpenAI. It delivers strong instruction following, sharp text rendering, and flexible sizing up to 4K.

Seedance 2.0 Fast R2V by ByteDance is the faster and lower-cost variant of Seedance 2.0 R2V, accepting reference images, videos and audios at 480p / 720p (1080p not supported).

Snap your fingers and freeze the world around you in a cinematic time-stop video. 62 scenarios across viral 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.

Seedance 2.0 Fast by ByteDance generates short MP4 videos faster and cheaper than Seedance 2.0, with the same multimodal capabilities, limited to 480p / 720p output.

Reconstruct a 3D scene from multi-view photos or a short video. Produces 3D Gaussian splats with depth maps and cameras, plus a colored point cloud.

Seedance 2.0 R2V generates short cinematic videos from reference clips, images, and optional audio, with synchronized sound and strong motion control.

Seedance 2.0 by ByteDance generates short MP4 videos from text, with optional image and audio references. It supports synced audio, stable motion, and cinematic camera direction.

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

Grok 4.1 Fast by xAI is a long-context chat model built for tool calling and agent workflows. It can analyze images and return grounded text answers with sources.

Grok 4.20 is xAI’s flagship text model with a 2M-token context window, tool calling, and structured JSON outputs. Attach images for vision Q&A and OCR.

14B Real-Time Long Video Generation Model