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

Split Screen LoRA for Wan

Prompt

Split Screen. Side-by-side reflection shot. Left video: handheld shot of vacuum cleaner sucking up dust and debris across hardwood floor. Reflection: aerial documentary footage of tornado funnel touching down in open field, debris spiraling upward. No visible dividing line or gap between them.

Prompt

Split Screen. Side-by-side reflection shot. Left video: macro shot of match being struck against matchbox, flame bursting to life, sulfur igniting. Reflection: night sky footage of lightning bolt striking ground during thunderstorm, electric branch illuminating clouds. No visible dividing line or gap between them.

Prompt

Split Screen. Top-bottom flat reflection shot. Top: tea bag being dunked into hot water in clear glass mug, dark tea clouds billowing outward and downward. Reflection: real documentary footage of parachutist descending through clouds, parachute fully deployed, sky diver silhouetted against sky. No visible dividing line or gap between them.

Prompt

Split Screen. Seamless horizontal split screen. Top half: hands rolling out dough with wooden rolling pin on floured kitchen counter, smooth back-and-forth motion. Bottom half: massive industrial steamroller flattening fresh asphalt on city street, heat waves rising. The rolling motions are perfectly synchronized.

Prompt

Split Screen. Seamless vertical split screen: On the left, tight shot of kitchen blender with fruit smoothie ingredients swirling violently inside clear glass container. On the right, construction site cement mixer rotating slowly, wet concrete tumbling inside large industrial drum. Both rotating in same direction.

---

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 specializes in creating dynamic split screen compositions that juxtapose contrasting or complementary scenes. It can create various split screen configurations including side-by-side reflections, top-bottom flat reflections, and seamless horizontal or vertical divisions. The model excels at finding visual connections between seemingly unrelated subjects, creating thought-provoking juxtapositions that tell a story through visual contrast.

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

Trigger Words

The trigger phrase is Split Screen.

For best results, start your prompt with "Split Screen" followed by a description of the two scenes you want to juxtapose and how they should be arranged (side-by-side, top-bottom, etc.). The model will create a seamless composition that highlights the relationship between the two scenes.

Setup for ComfyUI

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

• Download [WAN2.2]SplitScreen_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]SplitScreen_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