# The well

> An animal-noir mystery begins with a wolf found at the bottom of a well. Furred characters, snowy streets and dim rooms share a restrained teal palette and pools of warm light.

- Kind: Video
- Page: https://meetreference.com/v/ref-runway-the-well/
- Ready-to-use agent handoff: https://meetreference.com/v/ref-runway-the-well/agent.txt
- Authorship: AI-made, per the source
- Made with: Not stated
- Model: not stated
- Built with: not stated
- Style: Short films; neo-noir, anthropomorphic, cinematic, low-key lighting, winter, photorealistic, desaturated
- Length and format: 5 min, 16:9 (1280x720 source)
- Playback: a muted visual reference. The original soundtrack is available only at the source.
- Shared by Dorian & Daniel in YouTube: https://www.youtube.com/watch?v=yBs_pMUDrrk
- Prompt fidelity: Unavailable in this entry. The recreation brief is written by Reference.

## Before you start

Guidance from Reference, separate from the creator's instructions.

1. Read the reference and inspect the project, installed libraries, and available agent skills before writing code. Reuse suitable tools already present.
2. Prefer the creator-reported libraries and skills when they fit the task. Explain what useful additions help with, and install missing project dependencies or relevant skills from official sources when the environment and the user's existing permissions allow it. Respect the project's package manager and setup rules; do not ask again for routine setup already authorized.
3. Distinguish tools used by the creator from your own recommendations. A listed tool is not automatically required, and an empty tools or requirements list means the setup is unknown, not that nothing is needed.
4. Ask concise questions when missing inputs or choices materially affect the result: paid services, credentials, the user's assets, or a different production approach. Use existing answers and permissions; continue independent work while waiting.
5. If a useful library, skill, or service cannot be installed or used, explain an available alternative and its expected effect on quality, features, or effort. Get the user's choice before a material compromise; otherwise state the fallback and continue. Never silently simplify the result or claim to have used a tool you did not use.

## Recreating this video

This is a visual reference. No original creator prompt is available. The following brief was written by Reference after inspecting the work.

Ground an unusual character concept in familiar, materially detailed environments rather than making every element fantastical. Adapt the cold blue-green shadows, isolated amber practical lights, and alternation between spatial overviews and tight portraits. For a new subject, replace the animal cast, uniforms, and evidence props while retaining the restrained palette and strong foreground-background separation. Keep any closing typography small and centered over a tactile detail shot.

1. Open the live work or source and inspect the frame images below.
2. Adapt its layout, hierarchy, palette, and interaction patterns to the user's own content and brand.
3. Compare the result against the reference. Use your own assets and credit the original creator.

## What it looks like

Written by Reference from the video frames, not by the creator.

Moody, cinematic scenes featuring anthropomorphic animal characters in a shadowy interior.

- Color: Muted teal, blue-green, charcoal, and black, with small warm red and amber accents.
- Type: No prominent typography appears in the nine sampled scenes; the wider inspected film ends with small pale serif credits.
- Framing: A brief view across a vehicle-like dashboard followed by medium close-ups and close-ups of animal characters, mostly framed against dim indoor backgrounds.
- Structure: A view through a rain-speckled windshield, alternating hare and cat portraits in a dim room, a wolf outdoors, then close views of the hare and a bespectacled horned character.

Storyboard, nine frames spread across the video: https://meetreference.com/media/ref-runway-the-well/storyboard.webp

- Frame 1 at 18.3s: https://meetreference.com/media/ref-runway-the-well/f1.webp
- Frame 2 at 54.8s: https://meetreference.com/media/ref-runway-the-well/f2.webp
- Frame 3 at 91.4s: https://meetreference.com/media/ref-runway-the-well/f3.webp
- Frame 4 at 128.0s: https://meetreference.com/media/ref-runway-the-well/f4.webp
- Frame 5 at 164.5s: https://meetreference.com/media/ref-runway-the-well/f5.webp
- Frame 6 at 201.1s: https://meetreference.com/media/ref-runway-the-well/f6.webp
- Frame 7 at 237.7s: https://meetreference.com/media/ref-runway-the-well/f7.webp
- Frame 8 at 274.2s: https://meetreference.com/media/ref-runway-the-well/f8.webp
- Frame 9 at 310.8s: https://meetreference.com/media/ref-runway-the-well/f9.webp

## Links

- Watch: https://www.youtube.com/watch?v=yBs_pMUDrrk
- Original post: https://www.youtube.com/watch?v=yBs_pMUDrrk
- Runway AI Festival 2026 — official credits and synopsis: https://aif.runwayml.com/