Join our Discord community where you can generate videos, share ideas and request LoRAs, to push the bounds of the technology!
HUNYUAN v1.0 :
Trained on Hunyuan Video fp8 with 19 images of Erza Scarlet in various episodes of Fairy Tail.
The trigger word is: "3zr4_8c4 Erza Scarlet, red hair,"
Recommended Settings:
LoRA strength = 1.0
Embedded guidance scale = 7.0
Flow shift = 17.0
Prompt Recommendations:
Best to keep the prompt relatively simple, here are some examples that have worked well for me:
Example 1: 3zr4_8c4 Erza Scarlet, red hair is the main subject and is positioned in the foreground of the image. She is wearing a revealing thong nailon suit and has her right hand on her hip. Her left hand is clenched into a fist and is positioned close to her waist. She is facing towards the right of the image, but her head is turned slightly to the left and she is looking directly at the viewer. Her expression is confident and slightly smug. Her hair is pulled back into a high ponytail and she is wearing a small, white, flower-shaped hair ornament. There are no other characters visible in the image. She is moving her hips
Example 2: 3zr4_8c4 Erza Scarlet, red hair, Fairy Tail anime style, walks in a moonlit forest, surrounded by glowing fireflies which are flying in the background. Her enchanted sword is strapped to her back, and her crimson cape flutters as she surveys the area with sharp eyes.
Let me know if there are any questions, I'll be happy to help!