Create a Product Video
A short clip of a ring turning under light sells the piece in a way a still can't. This workflow takes a finished design to a channel-ready product video. The one trick to internalize: the video inherits everything from the still it starts from, so all the polishing happens before you ask for motion.
Step 1. Finish the still first
Materials, scene, lighting, and framing all carry over from the source image into the clip. Fix anything that bothers you in the image; it's faster and more precise than trying to fix it in a video. Two steps are worth doing now, while they are quick. Run Upscale to 4K on the still: a sharp source gives a sharp clip, and the clip itself comes back in full HD (1080p), with 4K a chat request away. Run Remove background if you want the piece isolated or on a clean scene. See Upscale to 4K and Remove background.
Step 2. Ask for one camera move
The quick path: right-click the still and choose AI Tools › Generate video, then pick the camera move (Turntable, Slow push in, Orbit, Contour flyover or Macro drift). The clip is always made from that image, and the job shows in the AI Operations tab. To start from a moment in an existing clip, pause the video on that frame first, then choose Generate video under Current frame in its AI Tools menu: that frame is the start frame.
The chat gives you more control. Add the still to the chat, then describe the motion in your own words: “Generate a turntable video of this ring.” With one still, that still becomes the first frame. You can attach more than one image. The first image you add is the start frame, the last one is the end frame, and anything in between guides the motion along the way. Say it in the prompt too, for example with two stills: “Start on image 1, the front view, and end on image 2, the three-quarter view.” Clips come back in full HD (1080p); add “in 4K” to the request if you need more. Name one motion per request, the same way you’d make one change per prompt: a turntable spin for a catalog page, a slow zoom onto the center stone for a hero shot, light sweeping across the metal for social. Stacking motions in one request muddles all of them.
Heads up
Tell the chat what to work from. Add the still (or, to change an existing clip, the video) to the chat before you ask. If nothing is attached, BLNG works from the canvas thumbnail, a single still of everything on the artboard, so you would get the whole board rather than the piece. With several images attached, the first is the start frame and the last is the end frame.
Step 3. Review and refine
Hover the video tile in the Chat to scrub through it in place; click for the full player. If the motion isn’t right, ask again with a sharper description: “slower”, “a full rotation”, “keep the camera still”. BLNG does not retry a failed video automatically: use Try again on the tile, or in the AI Operations tab if you made the clip from the image menu. In the AI Operations tab it makes a fresh attempt with the same settings and camera move; on the chat tile of a clip made from the image menu, it asks you for the camera move again. To try a different move, choose AI Tools › Generate video again and pick another one. Each request is a fresh clip from the same still, so you lose nothing by iterating. Need more resolution? Ask the chat to “upscale this video to 4K”.
Step 4. Export for the channel
Download from the tile for an MP4: the safe choice for e-commerce pages and social. If you removed the background or cropped the clip to a shape and need transparency, add the video to the canvas and choose Download WebM from the layer's Export menu instead. All plans can download videos. See Video on the Canvas.
For the mechanics of video generation, the tile, the player, and what can and can't be done to a clip, see Video on the Canvas.