用戶LoRA
XL Fantasy warriors
- 上傳時間
- 2023年8月13日 下午2:30
- 使用數
- 3.58k
- 評論
- 暫無評論
- 觸發詞
holding sword, armor, holding weapon, hailoknight
- 許可權
- 允許圖片生成與分享
- 允許使用者下載此模型
- 允許生成圖片用於商業用途
描述
Things To know: You should use the trigger words armor, holding sword, holding weapon, (For best results)
Works with swords and without. OBS. if you are going to generate pictures with swords have patience, but I have found that SDXL is actually good with swords!
This model is trained on dreamshaperXL10, but i have gotten much better results with sdxlUnstableDiffusers
Usage Tips : The LoRA weight I have been using is 1, but feel free to try and experiment!
I have used ComfyUI when generated pictures and the settings im using are: Sampler: dpmpp_2m Scheduler: Karras Steps: 30
For A1111 enjoyers, I would use: Sampler: DPM++ 2M Karras Steps: 36
Example prompts used: "full body shot of 1man, male, solo,wearing white armor, holding green weapon infront of him, holding green sword, white wings, simple glowing background, HD, masterpiece, best quality, hyper detailed, ultra detailed" And "1man. male, solo, wearing gery tech armor, holding glowing weapon infront of him, holding glowing sword, robot wings, simple glowing background, HD, masterpiece, best quality, hyper detailed, ultra detailed"
Every picture is generated in 1024*1024 with no upscale
Recomended vae that I use is the official sdxl_vae
https://civitai.com/models/126751/xl-fantasy-warriors-by-hailoknight