Home › Video Models › minimax/video-01-director

minimax/video-01-director - AI Video Models Tool

Overview

minimax/video-01-director (a Hailuo Video-01 “Director” variant from MiniMax) is a short-form, cinematic text→video and image→video model that emphasizes directorial camera control. The model produces HD 720p video at 25 fps and currently generates clips up to six seconds long; it was released as part of MiniMax’s Video-01/Hailuo family and later expanded with “Director” variants to expose camera movement controls for filmmakers and creators. ([minimax.io](https://www.minimax.io/news/video-01?utm_source=openai)) Users control camera motion using bracketed commands (for example: [Pan left], [Push in], [Tracking shot]) or by describing movement in natural language; the model supports combining up to three simultaneous or sequential movements for a single prompt. The API and playground also accept an optional first_frame_image (image-to-video) to lock aspect ratio and subject framing, plus convenience parameters such as a prompt optimizer and a camera_movement preset or 'Random' option. Community and third‑party playgrounds host examples and report the model produces cinematic-style pans, trucks, tilts, and tracking shots suitable for storyboarding, advert previsualization, and short social clips. ([internal.replicate.com](https://internal.replicate.com/minimax/video-01-director/readme?utm_source=openai)) MiniMax positions the Director models as higher‑control variants of Hailuo’s video engine (improved prompt adherence and reduced movement randomness). Official platform docs and the Replicate model pages document the technical fields and recommended prompt structure; pricing and per‑request billing vary by platform and are not consistently published on the Replicate model page. ([minimax.io](https://www.minimax.io/news/01-director?utm_source=openai))

Key Features

  • Cinematic camera controls via bracketed commands (e.g., [Pan left], [Push in]).
  • Supports up to three simultaneous or sequential camera movements per prompt.
  • Generates 720p, 25 fps videos — short clips focused on high visual fidelity.
  • Text-to-video and image-to-video modes; first_frame_image preserves aspect ratio.
  • Prompt optimizer and optional camera_movement parameter (including 'Random').
  • Improved prompt adherence and reduced movement randomness for predictable outputs.
  • Designed for storyboarding, advert previsualization, and short cinematic clips.

Example Usage

Example (python):

import os
import replicate

# Requires REPLICATE_API_TOKEN in environment
client = replicate.Client(api_token=os.environ.get("REPLICATE_API_TOKEN"))
model = client.models.get("minimax/video-01-director")

# Example: text-to-video with a bracketed camera movement
output = model.predict(
    prompt="[Push in] A solitary red fox pauses on a snowy ridge at sunrise, cinematic lighting, shallow depth of field.",
    prompt_optimizer=True,
)
print("Generated video URI:", output)

# Example: image-to-video (use first_frame_image to retain aspect ratio)
# output = model.predict(
#     prompt="[Tracking shot] The same fox runs through a misty pine forest.",
#     first_frame_image="https://example.com/first-frame.jpg",
#     prompt_optimizer=True,
# )
# print(output)

# Notes: field names and usage are documented on the model's Replicate API page. ([replicate.com](https://replicate.com/minimax/video-01-director/versions/455972c1d61cd32b05be9b412e63fb5811e179760299eb3023323a1630f9961b/api?utm_source=openai))

Benchmarks

Resolution & framerate: 720p (1280×720) at 25 fps (Source: ([internal.replicate.com](https://internal.replicate.com/minimax/video-01-director/readme?utm_source=openai)))

Maximum clip length: Up to 6 seconds (current major version) (Source: ([minimax.io](https://www.minimax.io/news/video-01?utm_source=openai)))

Input modes: Text-to-video and image-to-video (first_frame_image supported) (Source: ([minimax.io](https://www.minimax.io/news/video-01?utm_source=openai)))

Camera movement control: Bracketed commands and natural language; up to 3 combined movements (Source: ([internal.replicate.com](https://internal.replicate.com/minimax/video-01-director/readme?utm_source=openai)))

API fields of note: prompt, first_frame_image, camera_movement (optional), prompt_optimizer (Source: ([replicate.com](https://replicate.com/minimax/video-01-director/versions/455972c1d61cd32b05be9b412e63fb5811e179760299eb3023323a1630f9961b/api?utm_source=openai)))

Last Refreshed: 2026-01-09

Key Information

  • Category: Video Models
  • Type: AI Video Models Tool
Visit Official Website

Related Tools

Mochi 1

Mochi 1 is an open state-of-the-art video generation model by Genmo, featuring a 10 billion parameter diffusion model built on the novel Asymmetric Diffusion Transformer (AsymmDiT) architecture. It generates high-quality videos with high-fidelity motion and strong prompt adherence and is available via an API on Replicate.
Allegro

Allegro is an advanced open-source text-to-video generation model by RhymesAI. It converts simple text prompts into high-quality, 6-second video clips at 15 FPS and 720p resolution using a combination of VideoVAE for video compression and a scalable Diffusion Transformer architecture.
Mochi 1 Preview

Mochi 1 Preview is an open, state-of-the-art text-to-video generation model by Genmo that leverages a 10 billion parameter diffusion model with a novel Asymmetric Diffusion Transformer architecture. It generates high-fidelity videos from text prompts and is available under an Apache 2.0 license.
Stable Virtual Camera

A 1.3B diffusion model for novel view synthesis that generates 3D consistent novel views and videos from multiple input images and freely specified target camera trajectories. It is designed for research and creative non-commercial use.
Wan2.1-T2V-14B

Wan2.1-T2V-14B is an advanced text-to-video generation model that offers state-of-the-art performance, supporting both 480P and 720P resolutions. It is part of the Wan2.1 suite and excels in multiple tasks including text-to-video, image-to-video, video editing, and even generating multilingual text (Chinese and English) within videos. The repository provides detailed instructions for single and multi-GPU inference, prompt extension methods, and integration with tools like Diffusers and ComfyUI.
Veo 3

Veo 3 is an AI-powered video generation model from Google DeepMind that produces both visuals and native audio, including sound effects, ambient noise, dialogue, and accurate lip-sync. It delivers hyperrealistic motion, prompt adherence, and even can generate video game worlds, making it a versatile media generation tool.