metadata
tags:
- text-to-video
- diffusion
- merged-model
- video-generation
- wan2.1
widget:
- text: >-
A medium close-up of a blonde woman with blue eyes standing at a train
platform during golden hour. The camera dollies in slowly as she clutches
a small letter to her chest, wind lifting her hair. Her eyes search the
horizon with a mixture of hope and dread. The warm light of the setting
sun backlights her silhouette, casting long shadows behind her. The scene
feels bittersweet, suspended in time like a romantic drama climax.
parameters:
negative_prompt: >-
色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走
output:
url: images/ComfyUI_00001_.webp
base_model:
- Wan-AI/Wan2.1-T2V-14B
license: apache-2.0
🎥 Wan14BT2V_MasterModel
A powerful merged text-to-video model built on WAN 2.1, blended with the strengths of AccVideo, MoviiGen1.1, and CausVid.
📦 Downloads
Weights available in .safetensors format
👉 Download here
🔧 How to Use
from diffusers import DiffusionPipeline
pipe = DiffusionPipeline.from_pretrained("vrgamedevgirl84/Wan14BT2V_MasterModel")
video = pipe("A robot walks through a neon-lit alley during a rainstorm").video