zoom-no-olho

<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;"> <h1 style="color: #24292e; margin-top: 0;">Eye Close-Up LoRA for Wan2.1 14B T2V</h1> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Overview</h2> <p>This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos depicting close ups of any kind of eye you describe! This actually also works well on the Wan2.1 I2V models. As long as a clear close-up of a face is presented, the video should zoom into and showcase the eye of the subject close-up, as in the second example video.</p> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Features</h2> <ul style="margin-bottom: 0;"> <li>Trained on the Wan2.1 14B T2V base model</li> <li>Consistent results across different object and scenes types</li> <li>Simple prompt examples that are easy to adapt</li> </ul> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Community</h2> <ul style="margin-bottom: 0;"> <li><b>Discord:</b> <a href="https://remade.ai/join-discord?utm_source=Huggingface&utm_medium=Social&utm_campaign=model_release&utm_content=eye_close_up" style="color: #0366d6; text-decoration: none;">Join our community</a> to generate videos with this LoRA for free</li> <li><b>Request LoRAs:</b> We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!</li> </ul> </div> </div> <Gallery />

Model File and Inference Workflow

📥 Download Links:

• eye_10_epochs.safetensors - LoRA Model File
• wan_txt2vid_lora_workflow.json - Wan T2V with LoRA Workflow for ComfyUI

---

<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;"> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Recommended Settings</h2> <ul style="margin-bottom: 0;"> <li><b>LoRA Strength:</b> 1.0</li> <li><b>Embedded Guidance Scale:</b> 6.0</li> <li><b>Flow Shift:</b> 5.0</li> </ul> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Trigger Words</h2> <p>The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">3y3_cl053 eye extreme close up</code></p> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Prompt Template</h2> <p>For prompting, check out the example prompts; this way of prompting seems to work very well.</p> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">ComfyUI Workflow</h2> <p>This LoRA works with a modified version of <a href="https://github.com/kijai/ComfyUI-WanVideoWrapper/blob/main/example_workflows/wanvideo_T2V_example_02.json" style="color: #0366d6; text-decoration: none;">Kijai's Wan Video Wrapper workflow</a>. The main modification is adding a Wan LoRA node connected to the base model.</p> <img src="./workflow_T2V/workflow_screenshot.png" style="width: 100%; border-radius: 8px; margin: 15px 0; box-shadow: 0 4px 8px rgba(0,0,0,0.1);"> <p>See the Downloads section above for the modified workflow.</p> </div> </div> <div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;"> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Model Information</h2> <p>The model weights are available in Safetensors format. See the Downloads section above.</p> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Training Details</h2> <ul style="margin-bottom: 0;"> <li><b>Base Model:</b> Wan2.1 14B T2V</li> <li><b>Training Data:</b> Trained on 1 minute of video comprised of 18 short clips (each clip captioned separately) of various eye close-ups.</li> <li><b> Epochs:</b> 10</li> </ul> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Additional Information</h2> <p>Training was done using <a href="https://github.com/tdrussell/diffusion-pipe" style="color: #0366d6; text-decoration: none;">Diffusion Pipe for Training</a></p> </div> <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);"> <h2 style="color: #24292e; margin-top: 0;">Acknowledgments</h2> <p style="margin-bottom: 0;">Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!</p> </div> </div>