# AI use cases for Clipfactory (feyzilim/clipfactory) Repo: [feyzilim/clipfactory](https://github.com/feyzilim/clipfactory) | Use cases: 3 | Page: https://dedupedai.com/use-cases/feyzilim-clipfactory/ ClipFactory is a self-hosted pipeline that turns a topic and a template into a short vertical video from your own B-roll, or generates a full vertical video from a prompt in its AI Lab module. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Batch-produce short vertical videos from your own footage: https://dedupedai.com/use-cases/feyzilim-clipfactory/batch-vertical-videos-from-own-broll/ - Turn a single sentence into a fully AI-generated vertical video: https://dedupedai.com/use-cases/feyzilim-clipfactory/sentence-to-ai-generated-vertical-video/ - Build a TikTok photo carousel from a persona photo library: https://dedupedai.com/use-cases/feyzilim-clipfactory/tiktok-photo-carousel-from-persona-photos/ ## How to batch-produce short vertical videos from your own footage with Clipfactory Repo: [feyzilim/clipfactory](https://github.com/feyzilim/clipfactory) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Queue many topic-based 9:16 videos from clips you filmed, then review and publish them yourself. **Who it is for:** A creator or small brand team that already films b-roll and needs a steady stream of short vertical videos for TikTok, Reels or Shorts. **The problem:** Writing scripts, recording voice-overs, choosing clips and captioning each video by hand takes hours per video. **The outcome:** A set of finished 1080x1920 videos built from your own clips with AI script, AI voice and captions, each ready for your review before you post it. ### Steps 1. Run `git clone https://github.com/feyzilim/clipfactory.git && cd clipfactory`, then `docker compose up -d` and open http://localhost:3000. 2. On the Setup page, paste your OpenAI and ElevenLabs keys and test the connection, or tick Offline dry run to try it without keys. 3. Go to Personas, create a persona with the three-question wizard, and review the AI-drafted profile. 4. Open B-roll, generate the shot list, film the clips, then upload them with Add video or drop files into assets/ and run `make import`. 5. Open Projects, choose Batch, enter how many videos you want, pick templates and length, and let the topics come from AI. ### Prompt to paste into your agent ```text Use the repo feyzilim/clipfactory to set up a local instance with Docker and generate one test video for the persona on the topic . Run `make doctor` first to check keys and ffmpeg, then `make generate TEMPLATE=story_v1 TOPIC=""`. Expected output is a final.mp4 under storage/projects/. Verify that the file exists and that the video is 1080x1920. ``` ### Caveat Each video calls paid APIs, and the README asks you to watch your provider dashboards, and ClipFactory never posts videos for you. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/feyzilim-clipfactory/batch-vertical-videos-from-own-broll/ ## How to turn a single sentence into a fully AI-generated vertical video with Clipfactory Repo: [feyzilim/clipfactory](https://github.com/feyzilim/clipfactory) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README Use the AI Lab to build a storyboard, keyframes and animated segments from one prompt, without filming anything. **Who it is for:** A creator who has no footage for a concept and wants a complete short video generated from a written idea. **The problem:** Producing a vertical clip from scratch normally needs a camera, a set and an editor. **The outcome:** A concatenated 9:16 MP4 built from an LLM storyboard, chained keyframe images and per-segment video generation, with the option to redo single segments. ### Steps 1. Run `docker compose up -d` in the cloned Clipfactory folder and open http://localhost:3000. 2. On Setup or Settings, add an OpenAI key for keyframe images and a Google or fal.ai key for video generation. 3. Open the AI Lab and start a new video from your prompt. 4. Check the price estimate shown in the New-video dialog before you start, since retries and re-dos cost extra. 5. Review each segment, redo or edit any that miss, then download the finished MP4. ### Prompt to paste into your agent ```text Use the repo feyzilim/clipfactory's AI Lab to generate one vertical video from the prompt . Confirm the price estimate in the New-video dialog before starting, then save the concatenated 9:16 MP4. Verify that the output is a single MP4 with the expected length and aspect ratio. ``` ### Caveat The README puts AI Lab costs at roughly $1 to $15 per video depending on the model and length, so run a short test first. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/feyzilim-clipfactory/sentence-to-ai-generated-vertical-video/ ## How to build a TikTok photo carousel from a persona photo library with Clipfactory Repo: [feyzilim/clipfactory](https://github.com/feyzilim/clipfactory) | Difficulty: Intermediate | Time: 1 hour | Basis: From the README Use the Slideshow template to turn a one-liner script into a set of 1080x1920 slides with text on them. **Who it is for:** A creator who posts photo carousels on TikTok and wants them generated from a consistent set of persona photos. **The problem:** Choosing photos, writing short bold lines and adding text to each slide is repetitive when you post carousels often. **The outcome:** A set of 1080x1920 slide images with text on each, plus a zip file, ready to post as a photo post. ### Steps 1. Run `docker compose up -d` and open http://localhost:3000. 2. Add your photos under B-roll, then Photos, for the active persona. 3. On Generate, pick the Slideshow template and enter your topic. 4. Open the project page, review the 5 to 10 slides, and approve the set. 5. Download the zip and post the images as a photo post in the TikTok app, then pick a trending sound there. ### Prompt to paste into your agent ```text Use the repo feyzilim/clipfactory with the Slideshow template to create a photo carousel for the persona on the topic . Expected output is a set of 1080x1920 slide images plus a zip file. Verify that the zip contains one image per slide and that each image has text on it. ``` ### Caveat ClipFactory exports the slides but does not post them, and the trending sound has to be chosen inside TikTok itself. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/feyzilim-clipfactory/tiktok-photo-carousel-from-persona-photos/