Verified: 4 months ago
SafeTensor
Tencent Hunyuan is licensed under the Tencent Hunyuan Community License Agreement, Copyright © 2024 Tencent. All Rights Reserved. The trademark rights of “Tencent Hunyuan” are owned by Tencent or its affiliate.
Powered by Tencent Hunyuan
Request a LoRA on our Discord and we will train and open-source it for free.
Join our discord to generate videos of the Dog video LoRA for free.
HUNYUAN v1.0 :
Trained on 3 minutes of video taken from various dog videos. The model has a good understanding of different dog breeds and basic actions like running, walking, jumping, sitting, etc.
The trigger word is: 'dog video'
Recommended Settings:
LoRA strength = 1.0
Embedded guidance scale = 7.0
Flow shift = 17.0
Prompt Recommendations:
Best to keep the prompt descriptive, here are some examples that have worked well for me:
Example 1: dog video A small brown terrier is walking down a sidewalk, its leash gently swinging as it moves forward. The dog occasionally looks up, glancing at something off-camera before continuing its steady pace. The background features a quiet street lined with trees.
Example 2: dog video A Shiba Inu wearing a superhero cape is standing proudly on a hill, looking off into the distance. The cape flutters slightly in the breeze as the dog stands with its chest puffed out. The sky is bright blue with a few clouds, making it look like the perfect day for a hero.
Example 3: dog video A bulldog is wearing sunglasses and sitting in a kiddie pool filled with water. The dog doesn’t move much, just sitting contently as a garden sprinkler sprays water nearby. A bright yellow rubber duck floats in the pool next to the dog
Let me know if there are any questions, I'll be happy to help!