framelab - GitLite

KO | EN

gitlite — search

#gpt #anthropic #go #javascript #list #mysql #deep-learning #tensorflow #android #database

framelab

(★ 9)

FrameLab is a lightweight multimodal AI web app for cinematic media analysis.

File Explorer

ZIP Download

- - tests.yml
- INTERFACE.md
- REFERENCE.md
- TESTING.md
- TUTORIAL.md
- - 10_refine_with_image.meta.toml
  - 10_refine_with_image.txt
- - 10_image_deepdive.meta.toml
  - 10_image_deepdive.txt
  - 20_video_hybridscript.meta.toml
  - 20_video_hybridscript.txt
  - 30_script_cue_extraction.meta.toml
  - 30_script_cue_extraction.txt
  - 31_cue_refinement.meta.toml
  - 31_cue_refinement.txt
- - 02_general_assist.meta.toml
  - 02_general_assist.txt
  - 10_frame_breakdown.meta.toml
  - 10_frame_breakdown.txt
  - 11_shotlist_script.meta.toml
  - 11_shotlist_script.txt
  - 13_video_promptplan.meta.toml
  - 13_video_promptplan.txt
  - 15_cinema_mentor.meta.toml
  - 15_cinema_mentor.txt
  - 17_video_screenplay.meta.toml
  - 17_video_screenplay.txt
  - 20_screenplay_realization_checker.meta.toml
  - 20_screenplay_realization_checker.txt
- conftest.py
- test_app_state.py
- test_conversation.py
- test_live_llm_smoke.py
- test_llm_streaming_fallback.py
- test_llm_streaming_parsers.py
- test_run_helpers.py
- test_ui_smoke.py
.env.example
.gitattributes
.gitignore
.python-version
AGENTS.md
app_state.py
CHANGELOG.md
config.toml
conversation.py
hero.md
LICENSE
llm_streaming.py
pyproject.toml
README.md
requirements.txt
run.py
system_prompt.txt

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Version

File

Link

Example

# Project Badges

Latest Release Visit
License
Python

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

**FrameLab** is a lightweight multimodal AI app for cinematic analysis.
Bring text, images, or video, get streamed insights, then refine in a second pass.

🌐 **Use it on the web:** [framelab.streamlit.app](https://framelab.streamlit.app)

> [!TIP]
> 🔐 **Keep your API key secure:** FrameLab does not provide API credits. To run analyses (local or web), bring your own compatible API key in the sidebar, never share keys/screenshots publicly, and monitor token usage/cost on your provider account.

> [!IMPORTANT]
> **Vibecoding Disclaimer**: This project is built using an AI-assisted "vibecoding" approach (rapid iteration with human supervision). It is experimental, may contain bugs, and could break unintentionally during updates. Use it as a creative tool, but keep your expectations grounded.

---

https://github.com/user-attachments/assets/b03d8cea-ebce-4452-b27b-235f63dd173b

*Frame Breakdown — structured analysis of a single cinematic still.*

https://github.com/user-attachments/assets/15a06774-e178-4eae-8594-6dc19c8dc126

*Shotlist Script — turn reference images into a camera-ready shooting script.*

https://github.com/user-attachments/assets/92b126c1-3b80-444d-a5fc-8a9e9e0667c7

*Video-to-Screenplay — convert video footage into a production-ready screenplay.*

For full step-by-step walkthroughs, see [`docs/TUTORIAL.md`](docs/TUTORIAL.md).

---

## Why people use FrameLab

- **Text-only or multimodal** workflow (images/videos are optional)
- **Two-phase flow**: Primary Analysis → Refinement Loop
- **Live streaming output** with a Thought Process panel when available
- **Prompt and output editing** directly in the UI
- **Copy actions** for both plain text and markdown
- **Provider flexibility** via OpenAI-compatible endpoints

---

## Quick Start

FrameLab uses [`uv`](https://docs.astral.sh/uv/) for dependency + runtime management.

```bash
git clone https://github.com/taruma/framelab.git
cd framelab
uv sync
uv run run.py
```

Optional (recommended):

```bash
# Windows
copy .env.example .env

# macOS / Linux
cp .env.example .env
```

Then add your key to `.env` (for example `LLM_API_KEY=...`) or paste it in the sidebar at runtime.

---

## How it works

1. **Configure in the sidebar**
   - Choose provider/model and set API key/endpoint as needed.
   - Load a prompt preset, then edit it freely.

2. **Phase 1 — Primary Analysis**
   - Add optional reference media + prompt/context, then click **Analyze**.

3. **Phase 2 — Refinement Loop**
   - Add refinement notes and optional follow-up media to iterate on the result.

### Feature flags

- **Since v2.1.0:** POS highlighting controls are feature-gated and hidden by default.
- To enable locally, set this in `config.toml`:

```toml
[features]
pos_highlighting = true
```

---

## Prompt presets

You can customize behavior without editing app code:

- `prompts/system/`
- `prompts/initial/`
- `prompts/correction/`

Optional: add `name.meta.toml` sidecars (`title`, `description`, `order`) for cleaner UI labels.

---

## Documentation

- [`docs/INTERFACE.md`](docs/INTERFACE.md) — complete map of every UI element
- [`docs/TUTORIAL.md`](docs/TUTORIAL.md) — step-by-step walkthrough from first launch to advanced workflows
- [`docs/REFERENCE.md`](docs/REFERENCE.md) — technical/runtime details, advanced config, API behavior, contracts, troubleshooting
- [`docs/TESTING.md`](docs/TESTING.md) — testing strategy and commands
- [`CHANGELOG.md`](CHANGELOG.md) — release history and detailed changes
- [`AGENTS.md`](AGENTS.md) — AI contributor/agent rules and architecture constraints

---

## License

Distributed under the MIT License. See `LICENSE` for details.

---

Built with ❤️ by **Taruma Sakti** · Vibecoding with Cline + GPT-5.3-Codex