Google Gemini Omni Flash Enhances Adobe Firefly
Adobe has integrated Google’s Gemini Omni Flash into Firefly, expanding its AI-powered creative platform with conversational video editing capabilities. The addition allows creators to generate and edit videos using natural language prompts while working inside a unified creative workflow. Consequently, users can modify scenes, animate images, and refine videos without switching between multiple applications.
The integration reflects Adobe’s multi-model AI strategy, which combines Firefly’s proprietary models with leading third-party technologies. Moreover, creators can choose the AI model that best suits a specific project while remaining within the Firefly environment.
Conversational Video Editing Comes to Firefly
Gemini Omni Flash enables creators to edit videos through simple conversations instead of traditional editing timelines. Therefore, users can request changes such as replacing backgrounds, adjusting lighting, modifying camera angles, or restyling scenes with natural language instructions. The model preserves context between edits, allowing multiple refinements without starting over.
The model supports text, images, audio, and video as inputs. In addition, it can generate new video clips, transform uploaded media, and create consistent outputs across multiple editing rounds. Google designed Gemini Omni Flash to handle both video generation and conversational editing from a single multimodal interface.
Adobe says the integration gives creators greater flexibility while maintaining a professional production workflow. Matt Chotin, Senior Director of Product at Adobe, said, “We’re excited to bring Google’s newest models, including Gemini Omni Flash and Nano Banana 2 Lite, to Adobe Firefly, our all-in-one creative AI studio – to help creators move faster from idea to finished content. These new models build on Adobe’s strategy to deliver our pro-grade tools and the industry’s top creative AI models in a connected workflow, giving creators flexibility and control over how they bring their creative ideas to life.”
Faster AI Video Creation for Professionals
Gemini Omni Flash emphasizes speed alongside creative control. Therefore, creators can quickly iterate on ideas, generate variations, and make targeted edits without repeating the entire production process. The model also supports reference-based video generation, allowing users to combine multiple assets into cohesive outputs.
Google has priced Gemini Omni Flash at approximately $0.10 per second of generated video output for API usage, making it one of the company’s lower-cost video generation models. Furthermore, developers can access the model through Google AI Studio and the Gemini API, while Firefly users benefit from the integrated creative experience.
Adobe Expands Its Multi-Model AI Ecosystem
Adobe continues broadening Firefly by incorporating AI models from multiple providers rather than relying solely on proprietary technology. Consequently, creators gain access to specialized models for images, video, and design tasks within a single workspace.
The partnership also highlights increasing collaboration between leading AI companies and creative software vendors. As demand for AI-assisted content creation grows, conversational video editing is expected to become a core feature for professional designers, marketers, filmmakers, and digital content creators.
