Creative ideas often begin on the open web. A user may find a strong image on Pinterest, a useful motion example on Twitter or X, or a polished page on Awwwards.
The problem comes next. Moving those references into separate research, image, and video tools can break the connection between the first idea and the final asset.
Clico is an AI creative studio for image and video generation that connects online references, research, generation, and saved history.
Its browser extension supports exploration, while Clico Web brings the larger creative process into one tab.
Collect References From the Current Page
Clico’s browser extension works beside the page a user is viewing. It can use available page context, capture the visible browser tab, or capture a selected area when browser and site conditions allow it.
This helps creators collect visual direction from Pinterest, Twitter or X, Awwwards, and many other pages. One reference may provide a useful color palette. Another may show a clear layout. A short clip may suggest camera movement or pacing.
Users can add images and supported media attachments to the conversation. Video input depends on whether the selected model accepts that format. Some sites may also limit access because of protected content, embedded frames, or unusual page structures.
The goal is not to copy the source. The user should explain which quality matters and how it should guide an original result.
When the account, model, provider, quota, and generation settings support it, the extension can also generate and preview images in its chat panel. The complete video generation and playback workflow remains in Clico Web.
Create in One Web Tab
The project can continue in Clico’s AI media workspace. One Web tab can support public research, common files, image generation, video generation, and the conversation that connects them.
A creator may begin by researching an audience or visual trend. The findings can become a clear brief without starting a separate project. The same conversation can then create banners, covers, avatars, memes, carousels, or ordered image groups.
One image generation request can return up to four outputs. Users may select up to five owned image assets as references for the current image request. Only the chosen references need to guide the task, which helps keep private or unrelated uploads outside the generation.
After choosing an image direction, the user can move into video. A request may describe motion, aspect ratio, duration, resolution, or generated audio. Available settings depend on the internal video model profile.
Video generation takes place as a task. Queued and rendering states show progress, but the result is complete only when the finished MP4 is available.
Keep the Project Connected Through History
The extension can synchronize conversations with backend history. Users can reopen earlier chats and move into the fuller Web history experience.
A reference found while browsing can therefore stay connected to the explanation behind it. In Web, the saved conversation can include research, files, selected references, image options, and video instructions.
Clico Web also stores durable records for image and video generation. If a user leaves while a task is pending, reopening the conversation can restore the call and continue checking its status.
This is persistence for a defined task, not unlimited work without user direction.
Follow a Simple Five-Step Process
First, explore with a purpose. Look for one useful quality such as color, composition, mood, movement, or information structure.
Second, capture the reference and explain its role. Describe what should inspire the new work instead of asking for a copy.
Third, research the topic and write one descriptive brief. State the purpose, subject, audience, format, and intended feeling.
Fourth, generate a small set of image options and choose one direction before moving into video. Explain what should move and what should remain stable.
Fifth, review the completed files. Check spelling, product details, faces, hands, background objects, and motion. Confirm that you have permission to use every uploaded reference.
Reference-based generation improves direction, but it does not guarantee an exact match. Models may change lighting, objects, composition, identity, or text. Exact first-frame and last- frame video control also depends on the active model profile.
For teams, the best measure is not how many prompts were sent. It is how quickly the process produces an accurate asset that is ready for review. Clear references, a focused brief, and connected history can reduce repeated setup and unnecessary revisions.
From Explore to Free Creation
The browser extension keeps inspiration close to the page where it appears. Clico Web combines research, image creation, and video production in one tab. Synced history carries the project between them.
This creates a practical path from explore to free creation. Users still select the references, guide the idea, and approve the final work. Clico helps keep the context together from the first discovery to the finished image or video.
