
A swirling oil painting style with a somewhat thick brush texture, for Envy Starlight.
For best results (with Envy Starlight -- other checkpoints may differ), use strength 1.25 on the first pass and 2.0 on the highres pass (denoise set to 0.3 seems to work well).
Here's an A1111 module that supports that:
https://github.com/cheald/sd-webui-loractl
With that module installed, you can use this syntax:
<lora:EnvyStarlightSwirlOilPainting01:1.25:hr=2>
For an alternative use that retains a bit more of your checkpoint's existing style, do this instead:
<lora:EnvyStarlightSwirlOilPainting01:0@0,[email protected],[email protected]:hr=2.5>
This activates the LoRA at a higher strength part way through the generation, which gives you the brush stroke texture and smaller swirls, but respects the main model's composition a bit more. See below for examples of this.
描述:
训练词语: oil painting
名称: envyStarlightSwirlOil_01v10.safetensors
大小 (KB): 66128
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success