artificialguybr/WindowSeat-Redmond-WAN2-T2V-14B

Window Seat LoRA for Wan

Prompt

Window Seat. A handheld wide shot from inside a moving bus, slightly unsteady, looking through dirty windows at a one-room schoolhouse that sits isolated in the middle of a vast sunflower field in late summer. Through the schoolhouse windows, we glimpse a classroom where adult students—farmers, elderly people, middle-aged workers—sit at tiny children's desks, raising hands to answer questions. A young teacher in vintage clothing writes on a chalkboard. Golden pollen drifts through afternoon air. The sunflowers tower around the building, pressing against windows. Everything glows amber. There's a sense of timelessness, as if education continues outside of time in this forgotten place. Warm 16mm film grain, nostalgic color grading, Malick-inspired naturalism.

Prompt

Window Seat. From a plane window during turbulence: a vast desert below turns into a sea of mirror-like salt flats reflecting storm clouds. A lone horse gallops across the reflection, hooves barely disturbing the surface. Lightning forks above, mirrored below. Everything doubles—sky and ground indistinguishable. The hum of engines fades into silence.

Prompt

Window Seat. Through airplane window at cruising altitude: floating islands drift above cloud layer, connected by hanging bridges made of ropes and lanterns. Small figures walk across, carrying glowing jars. Lightning dances far below, illuminating the world's underside. Ethereal, painterly aesthetic, surreal realism.

Prompt

Window Seat. A locked-off shot from the interior of a moving subway captures the window view of an old theater stage where a single spotlight illuminates a giraffe standing center stage, neck extended upward, completely still as if delivering a monologue. Empty red velvet seats stretch into darkness. Dust particles float through the beam. A director sits alone in the front row, silhouette barely visible, taking notes. The giraffe's spotted pattern catches the theatrical lighting with almost painterly quality. Style: 1960s cinema verité meets Magritte, warm amber stage lighting against deep blacks, cinematic grain.

Prompt

Window Seat. Fixed side view from within a moving train, the window perfectly framing a surreal orchestral moment in an empty wheat field under stormy grey skies. Twenty cellists sit in formal concert dress on simple wooden chairs arranged in precise rows, their instruments reflecting dull light. They play in complete silence to the swaying wheat. Sheet music flutters wildly on stands. Dark clouds churn overhead, and a single shaft of light breaks through, illuminating the conductor—a small child in oversized tails, standing on a tree stump. The wheat field stretches endlessly. No audience exists. The performance continues. Filmed with cold blue-grey tones and high contrast, evoking Tarkovsky's contemplative surrealism and the absurdist theater of Beckett.

---

Special Thanks:
This project was made possible thanks to generous sponsorship and GPU time provided by reDMOND Ai.
We are grateful for their support in training this LoRA.

---

Model Description

This LoRA captures the contemplative, surreal experience of looking through windows while traveling. Each scene presents a view from buses, trains, planes, and trams that reveals extraordinary moments beyond ordinary reality - from floating islands above clouds to orchestras performing in wheat fields, from breathing forests to submerged cities. The style combines cinematic framing with surreal elements, creating dreamlike journeys that transform the mundane act of looking out a window into a portal to other worlds.

This version is specifically adapted for use with Wan-AI models, like Wan2.2-T2V-A14B.

Trigger Words

The trigger phrase is Window Seat.

For best results, start your prompt with "Window Seat" followed by a description of a view through a vehicle window that reveals something surreal or extraordinary. The model will render these scenes with a cinematic, contemplative quality.

Setup for ComfyUI

To use this LoRA in ComfyUI, simply place the file in your loras directory:

• Download [WAN2.2]WindowSeat_Redmond_high_noise.safetensors and place it in ComfyUI/models/loras/

Ensure your ComfyUI environment is already configured to run Wan models.

Example Workflow (ComfyUI)

In your ComfyUI workflow, add a Load LoRA node after your base model loader.

1. Load your base Wan model.
2. Connect the output of the model loader to the model input of the Load LoRA node.
3. Select [WAN2.2]WindowSeat_Redmond_high_noise.safetensors in the Load LoRA node.
4. Connect the MODEL output of the LoRA node to your KSampler.
5. Adjust the strength_model as needed (0.8-1.0 is a good starting point).

References

• Base Model: Wan-AI/Wan2.2-T2V-A14B
• ComfyUI: comfyanonymous/ComfyUI

---

🌐 Website

You can find more of my models, projects, and information on my official website:

• artificialguy.com

💖 Support My Work

If you find this model useful, please consider supporting my work. It helps me cover server costs and dedicate more time to new open-source projects.

• Patreon: Support on Patreon
• Ko-fi: Buy me a Ko-fi
• Buy Me a Coffee: Buy me a Coffee