Instructions to use Muapi/houshou-marine-wan2.1-14b-t2v with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Muapi/houshou-marine-wan2.1-14b-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/Wan2.1-T2V-14B-Diffusers", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Muapi/houshou-marine-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") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Houshou Marine/宝鐘マリン | Wan2.1 14B T2V
Base model: Wan Video 14B t2v Trained words: Houshou Marine, anime-style girl. The image features an anime-style character with hair styled in pink twin tails. The character has a confident and slightly smug expression, with their mouth slightly open and eyes looking to the side. They have a single eyepatch on one eye, which is black with a white border.The character's clothing includes a red and white outfit with gold accents. The top is a form-fitting, sleeveless dress with a high collar and a small bow at the neck. The dress is adorned with gold buttons and a decorative emblem on the chest. The character also wears a red scarf tied around their neck, adding to the pirate-like appearance. The outfit is completed with thigh-high boots that have gold trim and a small gold buckle.
🧠 Usage (Python)
🔑 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": "houshou-marine宝鐘マリン-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
- 5
