All Models

Gemini Omni 1.2 Flash Reference-to-Video creates synchronized audiovisual clips from a prompt and optional image or video references.

Seedance 2.5 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on ByteDance Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Alibaba WAN 3.0 Prime Reference-to-Video combines reference images, videos, and audio with prompts to create coherent videos with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Alibaba WAN 3.0 Reference-to-Video combines reference images, videos, and audio with prompts to create coherent videos with flexible 2-30 second duration, resolution, aspect ratio, audio, and deep-thinking controls. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedance 2.5 (Text-to-Video Turbo) generates cinematic videos from text prompts at 720p and 1080p with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability — optimized for turbo output. Built on ByteDance Seed's unified multimodal architecture. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Kling V4.0 Reference-to-Video builds a new clip of 3 to 30 seconds from up to 10 reference images, 5 reference videos and 3 reference audios, following the subjects, motion and camera you point to in the prompt, with 720p and 1080p output and synchronized stereo audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Open-weights MiniMax H3 reference-to-video: generate coherent 480p/540p/768p/1080p videos with native stereo audio guided by up to 9 reference images, 3 reference videos, and 3 reference audios.

Open-weights MiniMax H3 Singularity reference-to-video: generate coherent 480p/540p/768p/1080p videos with native stereo audio guided by up to 9 reference images, 3 reference videos, and 3 reference audios.

Open-weights MiniMax H3 Singularity reference-to-video: generate coherent 480p/540p/768p/1080p videos with native stereo audio guided by up to 9 reference images, 3 reference videos, and 3 reference audios, with custom LoRA support.

Open-weights MiniMax H3 reference-to-video: generate coherent 480p/540p/768p/1080p videos with native stereo audio guided by up to 9 reference images, 3 reference videos, and 3 reference audios, with custom LoRA support.

Kling V4.0 Flash Reference-to-Video generates a 3 to 20 second 720p clip guided by up to 10 reference images and 5 reference videos, with synchronized audio; Flash is the fast, lower-cost tier of Kling 4.0. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Generate a short video from up to seven reference images with xAI Grok Imagine Video v1.5.

MiniMax H3 Lite Reference To Video generates 4-15 second videos at 768p or 480p.

MiniMax H3 Highspeed Reference To Video generates 4-15 second videos at 768p.

MiniMax H3 is a 2K reference-to-video model that combines reference images, videos, and audio with natural-language instructions to create coherent video scenes.

Reference-guided video generation with images, videos, and audio, at 480p or 768p.

Alibaba Happy Horse 1.0 (Reference-to-Video) generates new video scenes guided by reference images, maintaining consistent characters, styles, and visual identity. Smooth camera movement and expressive, stable motion.

Alibaba Happy Horse 1.1 (Reference-to-Video) generates new video scenes guided by reference images, maintaining consistent characters, styles, and visual identity. Smooth camera movement and expressive, stable motion.

Gemini Omni 1.1 Flash Reference-to-Video creates synchronized audiovisual clips from a prompt and optional image or video references.

Create short videos guided by image and video references, with optional audio references and prompt-guided motion.

Gemini Omni Flash Reference-to-Video creates short videos from one or more reference images and a prompt.

Seedance 2.0 Mini is ByteDance's faster, lower-cost tier of Seedance 2.0 for cinematic multi-shot video — narrative sequences, AI camera control (zoom/pan/tracking), and consistent characters across scenes, from text or image prompts. 480p-4k, 4-15s, aspect ratios 16:9 / 4:3 / 1:1 / 3:4 / 9:16. Priced at 50% of standard Seedance 2.0.

Seedance 2.0 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on ByteDance Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedance 2.0 Fast (Text-to-Video) generates cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability — optimized for faster generation. Built on ByteDance Seed's unified multimodal architecture. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedance 2.0 (Text-to-Video Turbo) generates cinematic videos from text prompts at 720p and 1080p with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability — optimized for turbo output. Built on ByteDance Seed's unified multimodal architecture. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedance 2.0 Mini is ByteDance's faster, lower-cost tier of Seedance 2.0 for cinematic multi-shot video — narrative sequences, AI camera control (zoom/pan/tracking), and consistent characters across scenes, from text or image prompts. 720p-1080p, 5-12s, aspect ratios 16:9 / 4:3 / 1:1 / 3:4 / 9:16. Priced at 50% of standard Seedance 2.0.

Google Veo3.1 Reference-to-Video performs image-to-video generation that preserves a specific subject's appearance and identity from provided reference images, enabling consistent character or product motion across frames. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Alibaba WAN 2.7 Reference-to-Video turns character, prop, or scene references from images or videos into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Seedance 2.0 Fast (Text-to-Video Turbo) generates cinematic 720p/1080p videos from text prompts using speed-optimized inference —the fastest Seedance option with native audio-visual synchronization, director-level control, and exceptional motion stability. Built on ByteDance Seed's unified multimodal architecture. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Alibaba WAN 2.6 Reference-to-Video Flash turns character, prop, or scene references from images or videos into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Flash version with faster generation speed. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Alibaba WAN 2.6 Reference-to-Video turns character, prop, or scene references—single or multi-view—into new video shots with preserved identity, style, and layout plus smooth, coherent motion. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Supports audio generation. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

Kling Omni Video O3 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Supports audio generation. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

Kling Omni Video O3 (Standard) Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Supports audio generation. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

Reference to Video Q3 - Multi-Entity Consistency Video Generation

Reference to Video Q4 - Multi-Reference Video Generation

Kling Omni Video O1 Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Ready-to-use REST API, best performance, no cold starts, affordable pricing.

Kling Omni Video O1 (Standard) Reference-to-Video generates creative videos using character, prop, or scene references from multiple viewpoints. Extracts subject features and creates new video content while maintaining identity consistency across frames. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.

Google Veo 3.1 Fast Reference-to-Video generates 8-second videos from up to three reference images using the official Veo predictLongRunning endpoint with referenceImages assets.

SkyReels V4 Reference to Video generates videos from reference images or a reference video and a text prompt using the SkyReels V4 omni-video workflow.

Vidu Reference-to-Video 2.0 turns references into videos that preserve characters, objects, and environments with Multi-Entity Consistency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

X-AI Grok Imagine Video Reference-to-Video generates videos from multiple reference images with preserved identity, style, and scene composition. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Vidu Q2 is an Image-to-Video and Reference-to-Video model that emphasizes subtle facial expressions and smooth push-pull camera moves for natural motion. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

PixVerse V6 generates high-quality videos from images with flexible duration (1-15s), multiple resolutions up to 1080p, and optional audio generation. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Generate videos from reference images while keeping characters, objects, and scene identity consistent using Multi-Entity Consistency. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.