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

Followcam LoRA for Wan

Prompt

FollowCam. A continuous wide-angle shot following a lighthouse keeper climbing the spiral staircase inside a towering coastal lighthouse during a storm. She ascends steadily, one hand on the iron railing, the other carrying a maintenance kit. The narrow stairs wind upward in dizzying circles. Wind howls outside, rain lashing against small windows. The structure groans and sways slightly. Each window reveals glimpses of angry grey ocean below. She reaches the lamp room at the top, where massive rotating lenses cast sweeping beams into the tempest.

Prompt

FollowCam. A continuous first-person action shot from a chest-mounted camera as we follow a woman trail running through a dense, misty forest at dawn. She weaves between massive moss-covered trees, jumping over roots and dodging low branches. Her breath is steady and rhythmic. Fog clings to the ground, diffusing golden light that filters through the canopy. The path is uneven—rocks, mud, fallen logs. She never slows, her ponytail swinging with each stride. Birds scatter from the underbrush. The forest feels ancient and alive around us.

Prompt

FollowCam. A continuous handheld wide-angle shot following a motorcyclist tearing across endless white salt flats under a blazing midday sun. The rider leans forward, bike tilted into long arcs, kicking up plumes of salt dust that shimmer in the heat. The horizon is flat and infinite, sky meeting earth in a blurred line. Speed builds relentlessly—wind roars past the camera. The rider's silhouette stays centered ahead as the landscape blurs into white noise. No roads, no markers, just pure velocity across a blank canvas.

Prompt

FollowCam. A continuous underwater POV shot from a wide-angle action camera (~14mm) as we follow a diver swimming through a narrow submerged cave system. Her fins kick rhythmically ahead, illuminated by her headlamp cutting through murky blue-green water. Limestone walls close in on both sides, jagged and textured. Air bubbles trail upward in silvery streams. She squeezes through tight passages, her tank scraping against rock. Light from the surface is long gone—only her lamp and ours pierce the darkness. The water is cold and still. She moves with calm precision deeper into the labyrinth.

Prompt

FollowCam. A continuous wide-angle shot as we follow a rider on horseback galloping through a foggy meadow at dawn. The horse's powerful strides create a rhythmic thunder, muscles rippling beneath dark coat. Mist swirls around its legs with each impact. The rider sits low, reins loose, letting the horse run free. Trees emerge and disappear in the fog like ghosts. Wet grass flies up behind hooves. The horizon is invisible—just grey-white void. The horse knows the path instinctively, never slowing. Breath steams from its nostrils.

---

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 creates immersive, continuous "follow camera" shots that put viewers directly in the action. It generates dynamic footage where the camera follows subjects through various environments - from lighthouse staircases during storms to underwater cave explorations, from high-speed motorcycle rides across salt flats to peaceful library cart journeys. The style creates a sense of presence and movement that makes viewers feel like they're right there with the subject.

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

Trigger Words

The trigger phrase is FollowCam.

For best results, start your prompt with "FollowCam" followed by a description of a continuous tracking shot following a subject through an environment. The model will render these scenes with an immersive, action-oriented perspective.

Setup for ComfyUI

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

• Download [WAN2.2]Followcam_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]Followcam_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