Remade-AI/Animal-Documentary

Animal Documentary 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 an animal documentary!

Features

• Trained on the Wan2.1 14B T2V base model
• Consistent results across different object types
• Simple prompt structure that's 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

4n1m4l animal documentary The video shows a close-up of a chimpanzee grooming its infant, set against the backdrop of a lush green jungle.

Prompt

4n1m4l animal documentary The video shows a majestic lion resting in tall savanna grass, its golden mane catching the sunlight.

Prompt

4n1m4l animal documentary The video shows a tiger mother and her cub walking through a grassy field. The mother is larger and has more prominent stripes. The cub is smaller and its stripes are less distinct. They are both walking in the same direction.

Prompt

4n1m4l animal documentary a close-up of a scarlet macaw. The bird is perched on a branch and is facing to the left of the camera. Its feathers are a vibrant red, with blue and green accents. The macaw's large, black beak is slightly open, and its eyes are closed. The background of the video is a blurred out green foliage.

Model File and Inference Workflow

📥 Download Links:

• animal_doc_5_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: 4n1m4l animal documentary

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 4 minutes of video comprised of 51 short clips (each clip captioned separately) of various animal documentaries.
• Epochs: 5

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!