Recommended Prompts
aesthetic,artistic,creative,anime,illustrations,aerial
Recommended Negative Prompts
tiling,poorly drawn hands,poorly drawn feet,poorly drawn face,out of frame,extra limbs,blurry,body out of frame,bad anatomy,blurred,watermark,grainy,signature,cut off,draft,text,logo
Recommended Parameters
samplers | Euler, DPM++ SDE Karras, Euler a, DPM++ 2S a Karras | |
steps | 20-70 | |
cfg | 7-8 | |
resolution | 768×1024, 1024×1024, 1024×768 |
Recommended Hires (High-Resolution) Parameters
upscaler | 4x-UltraSharp | |
upscale | 1.5 | |
steps | 120-70 | |
denoising strength | 0.3-0.55 |
Tips
- Weight 0.8-1 is recommended but you can push more than 1 on less detailed render.
- Use ‘Aerial’ keywords for aerial photos.
Version Highlights
The V1 is OUT !!
Incredible good !!!!
Creator Sponsors
All sponsors are not affiliates of Diffus. Diffus provides an alternative online Stable Diffusion WebUI experience.
Please help me :
Add to your collection and share your creations here !
All Sample image are made Base SDXL_1.0 with Hi-res fix only – (No refiner)
This LoRas enhance/improve image to get more aesthetic/artistic/creative, detailled.
xl_more_art-full_v1 this version is little more photorealistic than betas but you can also do anime/illustrations.
Weight 0.8-1 is recommended but you ca push more than 1 on less detailled render. ^^
This LoRa also contains a training for aerial photos (use “Aerial” keywords), more details here : https://civitai.com/articles/2030/how-to-create-realistic-aerial-land-art