video_generator

Create videos from text prompts using cutting-edge AI models from top providers. Agent Forge's Video Generator brings powerful, creative video synthesis capabilities to your workflow—supporting diverse models, aspect ratios, resolutions, camera controls, native audio, and advanced style and consistency features.

Supported Providers & Models:

• Runway Gen-4 (Runway ML): Runway is a pioneer in text-to-video generation, known for powerful models like Gen-2, Gen-3, and Gen-4. The latest Gen-4 model (and Gen-4 Turbo for faster results) supports more realistic motion, greater world consistency, and visual references for character, object, style, and location. Supports 16:9, 9:16, and 1:1 aspect ratios, 5–10 second durations, up to 4K resolution, style presets, and direct upload of reference images for consistent generations. Runway powers creative tools for filmmakers, studios, and content creators worldwide.

• Google Veo (Google DeepMind): Veo is Google’s next-generation video generation model, offering high-quality, native-audio videos up to 1080p and 16 seconds. Supports advanced motion, cinematic effects, and nuanced text understanding. Veo can generate videos with built-in sound—activating native audio as well as silent clips. Options include 16:9 aspect, variable duration, different models (veo-3, veo-3.1), and prompt-based controls. Ideal for storytelling, advertising, research, and ideation.

• Luma Dream Machine (Luma AI): Dream Machine delivers jaw-droppingly realistic and fluid video from text. It incorporates advanced camera control, cinematography prompts, and supports both ray-1 and ray-2 models. Dream Machine supports precise aspect ratios (16:9, 9:16, 1:1), variable durations, and the specification of camera paths for intricate visual direction. Luma is renowned for breakthrough visual fidelity and is backed by leading AI vision researchers.

• MiniMax Hailuo-02 (via Fal.ai): MiniMax Hailuo-02 is a sophisticated Chinese generative video model, available globally through Fal.ai. Generate videos up to 16 seconds in landscape or portrait format, with options for prompt optimization to improve clarity and creativity. Pro and standard endpoints available, supporting high resolutions (up to 1920×1080). Well-suited for creative projects needing prompt translation and optimization, commercial storytelling, and rapid prototyping of visual ideas.

How to Choose: Pick your provider and model based on your needs for quality, speed, duration, audio, cost, and unique features. Runway and Veo offer world-leading realism and cinematic capabilities; Luma excels in fluid motion and camera control; MiniMax is ideal for Chinese-language prompts and offers fast, affordable access. Consider reference support, style presets, audio requirements, and pricing when selecting your tool.

For more details on features, restrictions, pricing, and model advances, see each provider’s official documentation above.

Usage Instructions

Generate high-quality videos from text prompts using leading AI providers. Supports multiple models, aspect ratios, resolutions, and provider-specific features like world consistency, camera controls, and audio generation.

Tools

video_runway

Generate videos using Runway Gen-4 with world consistency and visual references

Input

Parameter	Type	Required	Description
provider	string	Yes	Video provider (runway)
apiKey	string	Yes	Runway API key
model	string	No	Runway model: gen-4 (default, higher quality) or gen-4-turbo (faster)
prompt	string	Yes	Text prompt describing the video to generate
duration	number	No	Video duration in seconds (5 or 10, default: 5)
aspectRatio	string	No	Aspect ratio: 16:9 (landscape), 9:16 (portrait), or 1:1 (square)
resolution	string	No	Video resolution (720p output). Note: Gen-4 Turbo outputs at 720p natively
visualReference	json	Yes	Reference image REQUIRED for Gen-4 (UserFile object). Gen-4 only supports image-to-video, not text-only generation

Output

Parameter	Type	Description
videoUrl	string	Generated video URL
videoFile	json	Video file object with metadata
duration	number	Video duration in seconds
width	number	Video width in pixels
height	number	Video height in pixels
provider	string	Provider used (runway)
model	string	Model used
jobId	string	Runway job ID

video_veo

Generate videos using Google Veo 3/3.1 with native audio generation

Input

Parameter	Type	Required	Description
provider	string	Yes	Video provider (veo)
apiKey	string	Yes	Google Gemini API key
model	string	No	Veo model: veo-3 (default, highest quality), veo-3-fast (faster), or veo-3.1 (latest)
prompt	string	Yes	Text prompt describing the video to generate
duration	number	No	Video duration in seconds (4, 6, or 8, default: 8)
aspectRatio	string	No	Aspect ratio: 16:9 (landscape) or 9:16 (portrait)
resolution	string	No	Video resolution: 720p or 1080p (default: 1080p)

Output

Parameter	Type	Description
videoUrl	string	Generated video URL
videoFile	json	Video file object with metadata
duration	number	Video duration in seconds
width	number	Video width in pixels
height	number	Video height in pixels
provider	string	Provider used (veo)
model	string	Model used
jobId	string	Veo job ID

video_luma

Generate videos using Luma Dream Machine with advanced camera controls

Input

Parameter	Type	Required	Description
provider	string	Yes	Video provider (luma)
apiKey	string	Yes	Luma AI API key
model	string	No	Luma model: ray-2 (default)
prompt	string	Yes	Text prompt describing the video to generate
duration	number	No	Video duration in seconds (5 or 9, default: 5)
aspectRatio	string	No	Aspect ratio: 16:9 (landscape), 9:16 (portrait), or 1:1 (square)
resolution	string	No	Video resolution: 540p, 720p, or 1080p (default: 1080p)
cameraControl	json	No	Camera controls as array of concept objects. Format: [{ "key": "concept_name" }]. Valid keys: truck_left, truck_right, pan_left, pan_right, tilt_up, tilt_down, zoom_in, zoom_out, push_in, pull_out, orbit_left, orbit_right, crane_up, crane_down, static, handheld, and 20+ more predefined options

Output

Parameter	Type	Description
videoUrl	string	Generated video URL
videoFile	json	Video file object with metadata
duration	number	Video duration in seconds
width	number	Video width in pixels
height	number	Video height in pixels
provider	string	Provider used (luma)
model	string	Model used
jobId	string	Luma job ID

video_minimax

Generate videos using MiniMax Hailuo through MiniMax Platform API with advanced realism and prompt optimization

Input

Parameter	Type	Required	Description
provider	string	Yes	Video provider (minimax)
apiKey	string	Yes	MiniMax API key from platform.minimax.io
model	string	No	MiniMax model: hailuo-02 (default)
prompt	string	Yes	Text prompt describing the video to generate
duration	number	No	Video duration in seconds (6 or 10, default: 6)
promptOptimizer	boolean	No	Enable prompt optimization for better results (default: true)

Output

Parameter	Type	Description
videoUrl	string	Generated video URL
videoFile	json	Video file object with metadata
duration	number	Video duration in seconds
width	number	Video width in pixels
height	number	Video height in pixels
provider	string	Provider used (minimax)
model	string	Model used
jobId	string	MiniMax job ID

video_falai

Generate videos using Fal.ai platform with access to multiple models including Veo 3.1, Sora 2, Kling 2.5, MiniMax Hailuo, and more

Input

Parameter	Type	Required	Description
provider	string	Yes	Video provider (falai)
apiKey	string	Yes	Fal.ai API key
model	string	Yes	Fal.ai model: veo-3.1 (Google Veo 3.1), sora-2 (OpenAI Sora 2), kling-2.5-turbo-pro (Kling 2.5 Turbo Pro), kling-2.1-pro (Kling 2.1 Master), minimax-hailuo-2.3-pro (MiniMax Hailuo Pro), minimax-hailuo-2.3-standard (MiniMax Hailuo Standard), wan-2.1 (WAN T2V), ltxv-0.9.8 (LTXV 13B)
prompt	string	Yes	Text prompt describing the video to generate
duration	number	No	Video duration in seconds (varies by model)
aspectRatio	string	No	Aspect ratio (varies by model): 16:9, 9:16, 1:1
resolution	string	No	Video resolution (varies by model): 540p, 720p, 1080p
promptOptimizer	boolean	No	Enable prompt optimization for MiniMax models (default: true)

Output

Parameter	Type	Description
videoUrl	string	Generated video URL
videoFile	json	Video file object with metadata
duration	number	Video duration in seconds
width	number	Video width in pixels
height	number	Video height in pixels
provider	string	Provider used (falai)
model	string	Model used
jobId	string	Job ID

Notes

• Category: tools

• Type: video_generator