Instructions to use strangerzonehf/Wan2.1-t2v-14B-Person-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use strangerzonehf/Wan2.1-t2v-14B-Person-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
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("strangerzonehf/Wan2.1-t2v-14B-Person-LoRA") prompt = "A person, Yoga Routine: Develop a fitness video that guides viewers through a quick yoga routine for stress relief and relaxation. Include clear instructions on poses and breathing techniques. The video should be soothing and instructive, suitable for individuals seeking mindfulness and well-being." output = pipe(prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- Prompt
- A person, Yoga Routine: Develop a fitness video that guides viewers through a quick yoga routine for stress relief and relaxation. Include clear instructions on poses and breathing techniques. The video should be soothing and instructive, suitable for individuals seeking mindfulness and well-being.
Wan2.1-t2v-14B-Person-LoRA
Wan2.1-T2V-14B-Person-LoRA is a text-to-video adapter fine-tuned based on human preferences. It is built upon the Wan2.1-T2V-14B text-to-video model and has undergone 58 human data imprints over 2000 steps across 8 epochs.
Trigger words
You should use A person, to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Limitations
- Not suitable for complex indoor scenes.
- Not suitable for non-human characters.
- Downloads last month
- 202
Model tree for strangerzonehf/Wan2.1-t2v-14B-Person-LoRA
Base model
Wan-AI/Wan2.1-T2V-14B