
DoRA is trained on images of handguns.
DoRA weight: I recommend using the DoRA weight between 0.75 and 0.85. I personally use 0.75.
Recommended model: DoRA is trained on the base SDXL 1.0 model, so I think it's okay to use this DoRA on any model that is based on SDXL 1.0 (except anime models). I used the Juggernaut XL checkpoint to generate the images.
Clip skip: The clip skip of the DoRA is 1.
Usage guide: Use pistol/revolver words to trigger DoRA. You can also use the words cyberpunk/futuristic with pistol/revolver. You can also add color to the handgun and background. Use a resolution of 1344x768 when generating the image.
Example prompt: a render of a futuristic pistol with blue and white body, black background
This DoRA is far from perfect in drawing handguns. I trained it for fun.
描述:
训练词语: pistol,revolver
名称: handgunConceptDora_v10.safetensors
大小 (KB): 467819
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success