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-Diffusers", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Muapi/kisaragi-ren-wan2.1-14b-t2v")
prompt = "A man with short gray hair plays a red electric guitar."
output = pipe(prompt=prompt).frames[0]
export_to_video(output, "output.mp4")Kisaragi Ren/ε¦ζγγ | Wan2.1 14B T2V
Base model: Wan Video 14B t2v Trained words: Kisaragi Ren, anime-style girl. The image features a character with dark hair styled in loose waves. The hair is predominantly black with some purple highlights. The character has large, expressive eyes that are a mix of brown and purple, giving them a striking appearance. They are wearing a black shirt with the sleeves rolled up to the elbows, revealing a red vest underneath. The vest has a high collar and is buttoned down the front. Around their neck, they have a delicate necklace with a small pendant.
π§ Usage (Python)
π Get your MUAPI key from muapi.ai/access-keys
import requests, os
url = "https://api.muapi.ai/api/v1/wan21_t2v"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality",
"lora_model": "kisaragi-renε¦ζγγ-wan21-14b-t2v",
"lora_strength": 1.0,
"width": 832,
"height": 480,
"num_frames": 81
}
print(requests.post(url, headers=headers, json=payload).json())
- Downloads last month
- 7