Veo video generation model added (New Feature)

[Naveen56001]

Description

This PR resolves #85 issue. Added Veo video generation model with support for multiple generation modes, improved functionality, CLI integration, and documentation updates. This adds text-to-video, image-to-video, reference-image guided generation, and frame-based input support. Negative prompt support and full CLI commands for Veo were implemented.

Type of Change

• New feature (non-breaking change that adds functionality)
• Documentation update
• Performance improvement

Component Affected

• Video Generation (Luma AI / OpenAI Sora/Veo)

Changes Made

• Added Veo video generation model
• Implemented text-to-video generation
• Implemented image-to-video generation
• Added reference-image guided video generation
• Added frame-based input mode for video generation
• Added negative_prompt support
• Integrated full CLI commands for Veo
• Updated README with usage examples and CLI docs
• Validated all modes locally

Testing

• I have tested these changes locally
• New and existing unit tests pass locally with my changes

Test Environment

• Python Version: 3.10.19
• OS: Ubuntu 24.04.3 LTS (WSL2)
• GPU: N/A

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings

[github-actions]

PR Compliance Checks Passed!