# AI use cases for Printfilm (yi1108/printfilm)

Repo: [yi1108/printfilm](https://github.com/yi1108/printfilm) | Use cases: 4 | Page: https://dedupedai.com/use-cases/yi1108-printfilm/

PRINTFILM is a self-hosted, MIT-licensed Python and React platform that turns a topic or script into AI short videos and AI short dramas (comics with video), using TokenFree models.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run PRINTFILM locally with Docker in about 30 minutes: https://dedupedai.com/use-cases/yi1108-printfilm/try-printfilm-locally-with-docker/
- Turn a product topic into a finished short promo video: https://dedupedai.com/use-cases/yi1108-printfilm/make-short-promo-video-from-topic/
- Produce an AI short-drama episode with consistent characters: https://dedupedai.com/use-cases/yi1108-printfilm/build-episodic-short-drama-with-reusable-assets/
- Call the open API to generate images or videos from a script: https://dedupedai.com/use-cases/yi1108-printfilm/call-generation-api-from-script-or-agent/

## How to run PRINTFILM locally with Docker in about 30 minutes with Printfilm

Repo: [yi1108/printfilm](https://github.com/yi1108/printfilm) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Start the full stack on your own machine and open the user site, admin site, and API docs.

**Who it is for:** A developer or creator who wants to see the platform running before deciding whether to use it for real content.

**The problem:** Setting up a multi-service AI video platform by hand takes time, and the user needs to know it works before adding API keys.

**The outcome:** The user site at localhost:8080, admin at localhost:8081, and API docs at localhost:8000/docs are running, with the health check passing.

### Steps

1. Clone the repo with `git clone https://github.com/yi1108/printfilm.git`, then run `cd printfilm`.
2. Create the env file with `cp deploy/.env.docker.example deploy/.env.docker`, then set POSTGRES_PASSWORD, SECRET_KEY, and OPENAI_API_KEY / ARK_API_KEY. For a no-key preview, set ARK_MOCK=true.
3. Start the stack with `docker compose --env-file deploy/.env.docker up -d`, then wait about half a minute.
4. Check the API with `http://localhost:8000/api/health` in a browser or with curl, then open http://localhost:8080 and register at /auth.
5. Check status with `docker compose --env-file deploy/.env.docker ps` and read logs with `docker compose --env-file deploy/.env.docker logs -f api` if a service does not start.

### Prompt to paste into your agent

```text
In the printfilm repo, copy deploy/.env.docker.example to deploy/.env.docker, set ARK_MOCK=true and strong values for POSTGRES_PASSWORD and SECRET_KEY, then run docker compose --env-file deploy/.env.docker up -d. Output the status from docker compose ps and confirm that http://localhost:8000/api/health responds.
```

### Caveat

The README says the repo has no built-in demo account, so you must register first, and real image or video generation needs a TokenFree key instead of ARK_MOCK=true.

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/yi1108-printfilm/try-printfilm-locally-with-docker/

## How to turn a product topic into a finished short promo video with Printfilm

Repo: [yi1108/printfilm](https://github.com/yi1108/printfilm) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README

Pick a built-in style template and let the pipeline produce images, video, and a composed final cut.

**Who it is for:** A marketer who needs a short sales or education video for a product and does not have an editing team.

**The problem:** Producing a short promo video normally needs a script, storyboard, shots, and editing, which takes days of work.

**The outcome:** A composed short video, with storyboard and progress visible on the history page, ready to review and reshoot per shot.

### Steps

1. Start PRINTFILM and add a valid TokenFree key in deploy/.env.docker or in the admin site under 系统设置 → 模型.
2. Log in at http://localhost:8080 and open the AI 短视频 area.
3. Choose one of the 20+ built-in style templates and enter your topic or selling points.
4. Pick `full` for images plus video plus composition, or `image_text` for still images, which is faster and cheaper.
5. Track progress on the history page, redo a single shot if needed, and review the final cut in the preview.

### Prompt to paste into your agent

```text
Using the printfilm repo running at http://localhost:8080, create one AI short video for the topic <topic> with a built-in template in full mode. Report the project ID and the final composed video status, and confirm that every storyboard shot finished.
```

### Caveat

The README says generation needs a real TokenFree key, and it does not state any cost or quota numbers, so check your TokenFree balance before a large batch.

Risk, credentials: The TokenFree API key is entered in the env file or admin panel, so keep it out of Git and chat, and rotate it in TokenFree if it leaks.

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/yi1108-printfilm/make-short-promo-video-from-topic/

## How to produce an AI short-drama episode with consistent characters with Printfilm

Repo: [yi1108/printfilm](https://github.com/yi1108/printfilm) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README

Write an outline and script, store characters and scenes in the asset library, and turn episodes into shots.

**Who it is for:** A short-drama or comic writer who wants episodes with the same characters and locations across multiple chapters.

**The problem:** Keeping characters and scenes consistent across episodes is hard when every shot is made separately.

**The outcome:** A multi-episode AI 漫剧 project with reusable characters, scenes, and props, parsed into shots that can be edited and rendered.

### Steps

1. Log in at http://localhost:8080 and create an AI 漫剧 project.
2. Enter the outline, episode summary, or script content for each episode.
3. Add characters, scenes, and props to the asset library so they can be reused across episodes.
4. Parse the script into shots, then edit shots in the storyboard editor and canvas.
5. Generate video per episode, then check the episode output in the episode workbench.

### Prompt to paste into your agent

```text
Using the printfilm AI 漫剧 feature at http://localhost:8080, create a project named <project name> with the script in <script file>, add the recurring characters to the asset library, and parse episode 1 into shots. Report the shot count and confirm that each character is linked to its assets.
```

### Caveat

The README points to docs/EPISODE_RULES.md for episode rules, and this use case should be checked against that file before you rely on the episode output.

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/yi1108-printfilm/build-episodic-short-drama-with-reusable-assets/

## How to call the open API to generate images or videos from a script with Printfilm

Repo: [yi1108/printfilm](https://github.com/yi1108/printfilm) | Difficulty: Advanced | Time: 90 minutes | Basis: From the README

Use the /api/v1 endpoints with a Bearer token or X-Api-Key header to run generation from your own code.

**Who it is for:** A developer or automation agent that needs to generate images or videos as one step in a larger workflow.

**The problem:** Generation through the web interface does not fit into scripts, batch jobs, or other tools.

**The outcome:** A script or agent that submits image or video generation through PRINTFILM and receives results from the API.

### Steps

1. Start PRINTFILM and confirm the API is up with `http://localhost:8000/api/health`.
2. Open the API docs at http://localhost:8000/docs and find the /api/v1 image and video generation routes.
3. Obtain an API credential for your account, since the README names Bearer tokens and X-Api-Key headers but does not describe how to create one.
4. Send a request to the image or video route with either an `Authorization: Bearer <token>` header or an `X-Api-Key: <key>` header. (inferred, check the README)
5. Poll the task status through the API until the output is ready, then save the returned file.

### Prompt to paste into your agent

```text
Using the PRINTFILM API at http://localhost:8000/api/v1 and the route listed at http://localhost:8000/docs, submit one image generation request with the prompt <prompt> using the credential in <env var>. Return the task ID and the final result, and verify the response status is successful.
```

### Caveat

The README documents the /api/v1 paths and auth methods only in summary form, so confirm the exact request format in the /docs page before writing code against it.

Risk, credentials: API credentials and TokenFree keys grant access to paid generation, so store them in environment variables and never place them in prompts or committed files.

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/yi1108-printfilm/call-generation-api-from-script-or-agent/