Wan2.1 14B T2V LoRAs
Collection
A collection of Remade's Wan2.1 14B T2V LoRAs
• 20 items • Updated • 35
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import export_to_video
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Wan-AI/Wan2.1-T2V-14B", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Remade-AI/Dogs")
prompt = "d48g dog video A beagle puppy is sitting in a basket on a bicycle, ears flapping in the wind as the bike moves forward. The dog looks excited, glancing side to side at the passing scenery. The road is lined with trees, their leaves bright green."
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")Dogs LoRA for Wan2.1 14B T2V
Overview
This LoRA is trained on the Wan2.1 14B T2V model and allows you to generate awesome dog videos!
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
- d48g dog video A beagle puppy is sitting in a basket on a bicycle, ears flapping in the wind as the bike moves forward. The dog looks excited, glancing side to side at the passing scenery. The road is lined with trees, their leaves bright green.
- Prompt
- d48g dog video A Shiba Inu wearing a superhero cape is standing proudly on a hill, looking off into the distance. The cape flutters slightly in the breeze as the dog stands with its chest puffed out. The sky is bright blue with a few clouds, making it look like the perfect day for a hero.
- Prompt
- d48g dog video A Boston Terrier wearing a tiny suit and bow tie is sitting at a small dinner table. A candle flickers on the table as the dog stares at a fancy plate of steak in front of it. The background is softly lit, creating the feeling of a romantic dinner for one.
- Prompt
- d48g dog video A Pomeranian dressed as a tiny chef is sitting on a kitchen counter, staring at a bowl of cookie dough. It wears a little white chef's hat and apron while its fluffy tail wags. A wooden spoon rests next to the bowl, as if the dog is about to start baking.
Model File and Inference Workflow
📥 Download Links:
- dogs_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: d48g dog video
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 3 minutes of video comprised of 38 short clips (each clip captioned separately) of dogs.
- Epochs: 10
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!
- Downloads last month
- 20
Model tree for Remade-AI/Dogs
Base model
Wan-AI/Wan2.1-T2V-14B