𝐇𝐨𝐨𝐤 (LoRA) V1
Added 2023-07-11 08:06:09 +0000 UTCLoRA file
Wrestlings grumpiest twunk! I am releasing this as-is for free, this isn't as good as it could be and I need more training data. If you use LoRA block weights, set this one to :OUTALL for better results.
This is a LoRA trained on the 1.5 base SD model, at 768px. It is designed to be flexible and high quality. You'll need to be familiar with Stable Diffusion and LoRAs to use this!
Recommendations:
Trigger token: hook- Strength: 0.6-0.9, I usually start at 0.75
- Tags
- Use 'tattoos' for more accuracy
- He'll almost always generate with a necklace and his wrestling shorts, negative prompt those if needed
- Use 'brown eyes' in positive or 'blue eyes' in negative prompts for better results
- I recommend using After Detailer + Hires Fix, or IMG2IMG double upscaling using MultiDiffusion and ControlNet Tile for highly accurate faces
Terms: These models are designed for noncommercial use only, and are only for academic use. Commercial exploitation of the model or generations is strictly prohibited. It is the responsibility of you to ensure that your use complies with all applicable laws and regulations. By downloading this, you agree to adhere to these terms. If you do not agree, please refrain from using the model.
Returns & refunds: As the use of generative image creation is fundamentally complex and requires unique knowledge, including base models, prompting, additional resources, and more factors beyond our control, your dissatisfaction would be difficult to prove and therefore we have a no refunds policy. That withstanding, we will attempt to alleviate any issues directly.
