Klap
Klap utilizes artificial intelligence (AI) to identify interesting topics within the uploaded videos. It then generate edited short clips based of these topics, with intelligent framing to portrait and engaging captions.
Learn more
Gemini Omni Flash
Gemini Omni is Google’s new model family where Gemini’s ability to reason meets the ability to create, starting with video. The first model in the family, Gemini Omni Flash, can create anything from any input by combining images, audio, video, and text as input, then generating high-quality videos grounded in Gemini’s real-world knowledge. It gives users an easier way to edit video through conversation, where every instruction builds on the last, characters stay consistent, physics hold up, and the scene remembers what came before. Users can transform specific details or entire worlds, reimagine action, add new characters or objects, change environments, adjust camera angles, refine styles, and build multi-turn edits without losing the thread of the original scene. Gemini Omni is designed to bridge photorealism and meaningful storytelling by reasoning about what should happen next, using an intuitive understanding of forces like gravity, kinetic energy, and fluid dynamics.
Learn more
SeedEdit 3.0
SeedEdit is a generative AI image editing model from ByteDance’s Seed team that enables text-guided, high-quality image modification by applying natural language instructions to change specific parts of an image while maintaining consistency in the rest of the scene. Built on advanced diffusion and multimodal learning techniques, later versions like SeedEdit 3.0 improve on earlier releases with enhanced fidelity, accurate instruction following, and the ability to edit at high resolution (including up to 4K outputs) while preserving original subjects, backgrounds, and fine visual details. It supports common edit tasks such as portrait retouching, background replacement, object removal, lighting and perspective changes, and stylistic transformations without manual masking or tools, and achieves higher usability and visual quality than previous models by balancing between reconstruction and regeneration of images.
Learn more
Wan2.7 VideoEdit
Wan2.7 VideoEdit, available in Alibaba Cloud Model Studio, is an instruction-based AI video editing model designed to transform existing video content through natural language commands while preserving the original structure and motion. Instead of generating videos from scratch, it allows users to upload a source clip and describe desired changes such as modifying backgrounds, adjusting lighting, altering colors, applying stylistic transformations, or even changing elements like clothing, enabling iterative refinement without restarting the creative process. As part of the broader Wan2.7 multimedia system, it integrates seamlessly with other capabilities, including text-to-video, image-to-video, and reference-based generation, forming a unified workflow that supports creation, editing, continuation, and reshaping of visual content. The model emphasizes high-quality output with improved motion smoothness, visual coherence, and support for HD formats.
Learn more
