LoRA to immitate thermal vision camera. It's not very consistant, so you need to play with weight. Simple 1-2 words prompts are good eve with 0.5 weight, but as the prompts grow, you need to increase weight of LoRA higher up to 1.5

Model is not very consistent and tends to make regular images on the things, that it hasnt seen. I dont like how it turns out. Maybe in future, i'l make another version

Support

You can support me and request new lora's/checkpoints at: https://boosty.to/smgbuddies/donate

描述:

训练词语: thermalvision