Remade-AI/Tiny-Planet-Fisheye

Tiny Planet Fisheye LoRA for Wan2.1 14B T2V

Overview

This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate videos in the style of high distortion Little Planet fisheye!

Features

• Trained on the Wan2.1 14B T2V base model
• Consistent results across different object and scenes types
• Simple prompt examples that are easy to adapt

Community

• Discord: Join our community to generate videos with this LoRA for free
• Request LoRAs: We're training and open-sourcing Wan2.1 LoRAs for free - join our Discord to make requests!

Prompt

Little planet view fisheye lens The video depicts a Mars-inspired desert with towering red rock formations and swirling dust devils, all rendered into a miniature, spinning planet under a dusky sky.

Prompt

Little planet view fisheye lens The video shows a cyberpunk-inspired neon cityscape at night. Skyscrapers adorned with animated signs, pulsating lights, and digital effects twist into a compact, spherical world, evoking a futuristic dreamscape.

Prompt

Little planet view fisheye lens The video is a time-lapse of a bustling real-life metropolis, inspired by New York City. Skewed roads and twisting bridges form a miniature planet where the city lights pulse like stars in the night.

Prompt

Little planet view fisheye lens The video offers a unique view of Venice’s winding canals and ancient bridges. Gondolas drift along curving waterways that form a tiny planet, where reflections and ripples create a surreal, fisheye rendition of the historic city.

Model File and Inference Workflow

📥 Download Links:

• fisheye_15_epochs.safetensors - LoRA Model File
• wan_txt2vid_lora_workflow.json - Wan T2V with LoRA Workflow for ComfyUI

---

Recommended Settings

• LoRA Strength: 1.0
• Embedded Guidance Scale: 6.0
• Flow Shift: 5.0

Trigger Words

The key trigger phrase is: Little planet view fisheye lens

Prompt Template

For prompting, check out the example prompts; this way of prompting seems to work very well.

ComfyUI Workflow

This LoRA works with a modified version of Kijai's Wan Video Wrapper workflow. The main modification is adding a Wan LoRA node connected to the base model.

See the Downloads section above for the modified workflow.

Model Information

The model weights are available in Safetensors format. See the Downloads section above.

Training Details

• Base Model: Wan2.1 14B T2V
• Training Data: Trained on 2 minutes of video comprised of 26 short clips (each clip captioned separately) of various videos with the little planet fisheye distortion.
• Epochs: 15

Additional Information

Training was done using Diffusion Pipe for Training

Acknowledgments

Special thanks to Kijai for the ComfyUI Wan Video Wrapper and tdrussell for the training scripts!