base_model:
- Wan-AI/Wan2.2-I2V-A14B
tags:
- Image-to-Video
- lora
widget:
- text: >-
"Car Consistency. Used the car in the first frame, generate a
commercial-quality video of the car.The F1 car speeding on the ice field."
output:
url: assets/result (5).mp4
- text: >-
"Car Consistency. Used the car in the first frame, generate a
commercial-quality video of the car.The yellow car speeding under sea"
output:
url: assets/result (2).mp4
- text: >-
"Car Consistency. Used the car in the first frame, generate a
commercial-quality video of the car.The car speeding on the ice field"
output:
url: assets/result (3).mp4
CarConsistency-Wan2.2-I2V
- Prompt
- "Car Consistency. Used the car in the first frame, generate a commercial-quality video of the car.The F1 car speeding on the ice field."
- Prompt
- "Car Consistency. Used the car in the first frame, generate a commercial-quality video of the car.The yellow car speeding under sea"
- Prompt
- "Car Consistency. Used the car in the first frame, generate a commercial-quality video of the car.The car speeding on the ice field"
Description:
CarConsistency is the first model in this series. The goal of this model is to directly generate a highly consistent video of a vehicle(If the image input is a F1 car, the prompt should change from The car to The F1 car) from an input image (preferably on a white background) and a prompt (e.g., "the car is speeding on the moon/water/ice field,floating in the space..."). From the dozen or so images I've personally tested, CarConsistency can maintain a high degree of vehicle consistency, preserving details like the advertisements on a Ferrari SF25 race car, the Chinese characters on the license plates of an SU7 Ultra and a Fang Cheng Bao SUV, and the decorative patterns on the vehicles. Using the 'lightning-low' model for generation results in faster speed and more consistent quality.