# How Do I…(Quick Tasks) ### **How do I generate a thumbnail?** 1. Open Chat Video Pro inside Premiere Pro 2. Use the [**Frame Capture**](/getting-started/interface-overview/frame-capture-button.md) button to grab a frame from your timeline 3. Enter a prompt describing the thumbnail style (lighting, mood, text focus, etc.) 4. Select **GPT Image 2** (recommended for text overlay and complex compositions) or **Nano Banana Pro**, and enable **Thumbnail Mode** 5. Click **Generate** You can save the generated image directly for use on YouTube or social platforms. *** ### **How do I remove a background from an image or frame?** 1. Capture a frame or import an image into the chat 2. Ask Chat Video Pro to remove the background 3. Save the result as a transparent image if supported by the model This is useful for: * Overlays * Logos * Quick composites without external tools *** ### **How do I capture a frame from my timeline?** 1. Move the playhead to the desired frame 2. Click the [**Frame Capture**](/getting-started/interface-overview/frame-capture-button.md) button inside Chat Video Pro 3. The captured frame is automatically added to the chat composer This frame can then be used for: * Image generation * Image-to-video * Background removal * VFX concepts *** ### **How do I generate video content?** 1. Decide whether you’re generating: * [Text-to-video](/features/video-generation/text-to-video.md) * [Image-to-video](/features/video-generation/image-to-video.md) * [Video-to-video](/features/video-editing-tools/video-canvas-editor.md) 2. Provide the required input (text, image, or video) 3. Select a compatible video model 4. Enter a clear, concise prompt 5. Click **Generate** Start with short durations and lower resolutions to confirm the workflow before scaling up. *** ### **How do I add VFX without After Effects?** **Primary path — Kling O3 VFX on existing footage (3-10 seconds):** 1. Import your clip using the **Import Clip** button 2. Click **"Edit"** on the video thumbnail 3. Select **Kling VFX** from the mode dropdown 4. Describe the effect: `"Add heavy rain with wet streets"` or `"Make it nighttime with dramatic lighting"` 5. Optionally add a reference image and point to it with `@Image1` for more accurate results 6. Click **Edit Video** — original audio is preserved automatically **Power workflow:** First capture a frame → generate a styled reference image with Nano Banana → use that image as a guide for Kling VFX. "Show, don't tell" consistently outperforms text-only prompts. **For generating new VFX-style B-roll** (rather than modifying existing footage): use a standard text-to-video or image-to-video generation with a descriptive effect prompt. 👉 See [**Kling O3 VFX**](/features/video-editing-tools/kling-vfx.md) and [**VFX Workflow Guide**](/workflows/how-to-create-ai-powered-visual-effects-in-premiere-pro.md) for detailed walkthroughs. *** ### **How do I generate a transition?** 1. Add two images to Chat Video Pro to enter [**transition mode**](/features/video-generation/transition-mode.md) 2. Describe the transition style (glitch, blur, morph, energy, etc.) 3. Generate a short video clip 4. Place the generated clip between your two shots in the timeline For best results: * Keep transitions short * Match the color and motion direction of surrounding clips *** ### **How do I use Story tools for long footage?** Chat Video Pro can assist with: * Story analysis * Highlight identification * Editing suggestions based on transcripts Typical use cases: * Long interviews * Podcasts * Documentary footage For best results: * Export your transcript from Premiere Pro's **Text** panel (Window → Text → three dots ⋯ → **Export as transcript file**) as a **`.json` file** — SRT, VTT, and `.txt` files are not supported * Attach the `.json` file via the paperclip (📎) button in the Story Cutter conversation — a purple pill confirms it's loaded * Use clear instructions when prompting: include platform, runtime, and the goal of the video 👉 See [**Story Cutter workflows**](/conversation-starters/story-cutter-assistant.md) for the full guide including Insert Rough Cut, /batch, and creative brief support *** ### **How do I avoid wasting credits?** Best practices: * Start with a [reference image](/features/video-generation/image-to-video.md) * Dial in a prompt with the [video prompter](/conversation-starters/video-prompter-assistant.md) * Use a less expensive video model like Hailuo *** ### **How do I check what I’ve generated?** You can view usage in two places: * Inside Chat Video Pro: **Gear icon → Usage panel** * In your provider dashboard for full billing and job history * You can see all the generated media from the[ library](/getting-started/interface-overview/library.md) If something didn’t return to the panel, it may still exist in the provider dashboard. *** ### **How do I get help if I’m stuck?** If something doesn’t work: 1. Check [**Generation Errors & Failed Jobs FAQ**](/troubleshooting-and-faq/generation-errors-and-failed-jobs-faq.md) 2. Confirm[ **credits and API setup**](/getting-started/installation-and-activation.md) 3. Restart Premiere Pro If you still need help: * Use **Gear icon → Contact Us** * Or email support (listed in the About panel) Include: * What you were trying to do * Model used * Error message (if any) **Rather have your workflow built live?** Book a Founder Onboarding Session. We configure Chat Video Pro around your real project in 60 minutes — inside your Premiere timeline, with the founder — so you're running instead of searching. [BOOK YOUR SESSION →](https://checkout.chatvideopro.com/checkout/buy/6b983504-8882-45e4-9ca8-64ea1a28eddf) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.chatvideopro.com/troubleshooting-and-faq/how-do-i...-quick-tasks.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.