Balancing Act (Redmond) LoRA for Hunyuan

Prompt
Balancing Act. High-angle static shot of a chaotic, impossibly tall tower of vintage arcade game cabinets and electric guitars, precariously stacked on a windswept, rocky cliff overlooking a stormy sea. The machines and instruments, showing subtle wear, rust, and tear, are positioned upright, sideways, and tilted at improbable angles. The image has a photorealistic 35mm film look. The dramatic, dark clouds of the storm cast a tense, melancholic tone over the scene. The vastness of the churning ocean below accentuates the absurdity and surreal nature of the image.

Prompt
low-angle static shot of a massive, tangled helix of full suits of medieval knight's armor and brightly colored neon signs, precariously stacked in a clean, empty, modern subway station. The armor and glowing signs are positioned upright, sideways, and at improbable angles. The image has a photorealistic 35mm film look. The glow from the neon signs provides the primary light source, casting colorful, flickering shadows on the sterile tile walls and emphasizing the precarious structure. The anachronistic setting accentuates the absurdity and surreal nature of the image. Balancing Act

Prompt
A super low angle static wide shot from the bottom of a huge, empty concrete skatepark bowl, capturing a gigantic, chaotic static tower of rusted shopping carts, all balanced into a single, impossibly tall spire. The harsh, midday sun casts sharp, dark shadows across the smooth concrete curves. The 35mm film look brings out the grainy texture of the concrete and the peeling chrome of the carts. The camera lingers on the chaotic tower, emphasizing its sheer scale and precarious balance. Balancing Act

Prompt
High-angle static shot of a chaotic massive, huge, incredibly high arch of store mannequins and black grand pianos, precariously stacked on a long, empty airport runway under a flat, overcast sky. The mannequins, in various poses, and the grand pianos are positioned upright, sideways, diagonally, and tilted at improbable angles. The image has a photorealistic 35mm film look and realistic shadows, emphasizing the precarious nature of the structure. The vastness of the empty runway surrounding the arch accentuates the absurdity and surreal nature of the image. Balancing Act

Prompt
A high angle static shot capturing a huge, tall, enormous static stack of giant tortoises, all balanced into a tall, slow-moving tower in the middle of a vast salt flat. The bright, harsh sunlight casts long, dark shadows, emphasizing the sheer scale and texture of the pile. The 35mm film look brings out the cracked patterns of the salt flat and the ancient, wrinkled textures of the tortoises, creating a striking visual contrast. The camera lingers on the chaotic, yet stoic, tower. Balancing Act

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 imparts a surreal, artistic, and monumental style inspired by the "Balancing Act" series, originally conceived from Google's Veo model outputs. The aesthetic is characterized by large-scale, impossible sculptures that blend technology, classical art, music, and nature in a mesmerizing, often rotating, fashion.

This version is specifically adapted for use with the Tencent HunyuanVideo model.

Trigger Words

The trigger phrase is Balancing Act.

For best results, describe a grand, surreal sculpture or installation, and the model will render it in this unique aesthetic.

Setup for ComfyUI

To use this LoRA in ComfyUI, place the files in their respective directories:

LoRA: Download Hunyuan-BalancingAct-Redmond.safetensors and place it in ComfyUI/models/loras/
Diffusion Model: hunyuan-video-t2v-720p-q4_0.gguf (or other Hunyuan model) goes into ComfyUI/models/diffusion_models/
Text Encoders & VAE: Ensure your clip and vae models for Hunyuan are in ComfyUI/models/text_encoders/ and ComfyUI/models/vae/ respectively.

Example Workflow

You can load this LoRA using a standard "Load LoRA" node in ComfyUI. Connect it between your base model loader and the KSampler. Make sure to set the strength to your desired level (e.g., 0.8-1.0).

References

Base Model: tencent/HunyuanVideo
Original Style Inspiration: Google Flow / Veo
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

artificialguybr
/

Hunyuan-BalancingAct-Redmond-t2v-720p