Sign In

Frank Frazetta Style Lora

2.1k

Not recently loaded

Download

1 variant available

SafeTensor

562.72 MB

Verified:

Type
LoRA
Stats

719

9

57

Reviews
Published

Aug 12, 2025

Base Model
Training
Steps: 1,600Epochs: 16
Usage Tips
Strength: 1
Hash
AutoV2731A3DF625
Trigger Words
Frank Frazetta style.
iqff12.png

Frank Frazetta style lora. Hidream was clearly already pretrained on his images. This only took 800 steps to get it to produce images in his style.

Qwen 2.1 - This is a LoKr not a LORA. It should import the same way in comfyui. CFG should be between 2-3.5. 3 and 3.5 work well.