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.<hr /><h2 id="model-description">Model Description</h2>This LoRA imparts a surreal, artistic, and monumental style inspired by the "Bloom" series. The aesthetic is characterized by large-scale, impossible floral sculptures that blend technology, art, and nature in a mesmerizing, often cinematic, fashion inspired by Google Veo FLOW.This version is specifically adapted for use with Wan-AI models, like <code>Wan2.1-T2V-14B</code>.<h2 id="trigger-words">Trigger Words</h2>The trigger phrase is <code>Bloom</code>.For best results, describe a grand, surreal floral sculpture or installation, and the model will render it in this unique aesthetic.<h2 id="setup-for-comfyui">Setup for ComfyUI</h2>To use this LoRA in ComfyUI, simply place the file in your <code>loras</code> directory:<ul><li>Download <code>Wan-Bloom-Redmond.safetensors</code> and place it in <code>ComfyUI/models/loras/</code></li></ul>Ensure your ComfyUI environment is already configured to run Wan models.<h2 id="example-workflow-(comfyui)">Example Workflow (ComfyUI)</h2>In your ComfyUI workflow, add a Load LoRA node after your base model loader.<ol><li>Load your base Wan model.</li><li>Connect the output of the model loader to the <code>model</code> input of the Load LoRA node.</li><li>Select <code>Wan-Bloom-Redmond.safetensors</code> in the Load LoRA node.</li><li>Connect the <code>MODEL</code> output of the LoRA node to your KSampler.</li><li>Adjust the <code>strength_model</code> as needed (0.8-1.0 is a good starting point).</li></ol>

Files with SHA256: 2a5173ed0331d0b78f5d0696c11097d1bef132aaa9086ab401861e203f2d8596