How to use MelloModels/Mellos_HTTYD_Lora_for_WAN2.2_t2v 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/Wan2.2-T2V-A14B", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("MelloModels/Mellos_HTTYD_Lora_for_WAN2.2_t2v") prompt = "t00thle55, HTTYD2 Render Style, Hiccup. A low-angle tracking shot of a 3D rendered black dragon. The dragon flies rapidly through the clouds. The boy is wearing a green tunic, a brown fur vest, and leather boots. The dragon is in mid-flight with his body streamlined and angled slightly upward. His main wings are beating with powerful rhythmic downstrokes. The dragon's legs are tucked flush against his underbelly for aerodynamics. His tail and tail fins shift and tilt to steer through the turn. The dragon has a round head with black horns on the sides of his face along with long ears on the top of his head that are pulled back. The dragon has detailed black scales. The dragon tracks a flying object past the viewer's right. His green eyes are wide open showing his vertical slit pupils. He has a neutral expression with a closed mouth. The camera follows the subject from behind. The background is of a clear blue sky above a vast ocean. The lighting is neutral daylight." output = pipe(prompt=prompt).frames[0] export_to_video(output, "output.mp4")
How to use MelloModels/Mellos_HTTYD_Lora_for_WAN2.2_t2v with Wan2.2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
