V1 version of brocade mountain lora Description:
Chinese painting landscapes, the intention is first in the brush, the brush strokes convey the spirit.
This model is refined with Chinese ink and watercolor, focusing on traditional landscapes and courtyards and pavilions. Need to open high-resolution fix (Hires. fix) to ensure the quality of the map, there are problems can be commented on, see will reply, we more anti-map.
Recommended parameters:
Positive quality word reference:
liujin,chinese style architecture, pavilion, waterfall, outdoor, pine trees, panoramic view
Negative Tip Words Reference:
(worst quality:2),(low quality:2),(normal quality:2),text,error,missing fingers,extra digit,fewer digits,cropped,jpeg artifacts,signature ,watermark,username,blurry,dim light.
Big models: revAnimated v122, Mai Orange Realistic, 3D Character PLUS_v1.0, this lora generalization is higher, realistic, 3d, illustration class big models can try under.
Big model link: https://www.liblib.art/modelinfo/1004b01e19714137a593e30007f3c737?from=search、https://civarchive.com/models/43331/majicmix-realistic、https://civarchive.com/models/43331/majicmix-realistic
Lora weight: 0.8
Sampling method (sampler): Euler a + Karras (according to the actual situation can choose sampler)
Iteration steps: 24
CFG Scale: 7
Resolution reference: 512*768
High resolution fix (Hires. fix): 1. zoom algorithm: R-ESRGAN 4x+ Anime6B, 2. redraw amplitude: 0.3, 3. zoom speed: 2x
Description
V1 version of brocade mountain lora Description:
Chinese painting landscapes, the intention is first in the brush, the brush strokes convey the spirit.
This model is refined with Chinese ink and watercolor, focusing on traditional landscapes and courtyards and pavilions. Need to open high-resolution fix (Hires. fix) to ensure the quality of the map, there are problems can be commented on, see will reply, we more anti-map.
Recommended parameters]:
Positive quality word reference:
liujin,chinese style architecture, pavilion, waterfall, outdoor, pine trees, panoramic view
Negative Tip Words Reference:
(worst quality:2),(low quality:2),(normal quality:2),text,error,missing fingers,extra digit,fewer digits,cropped,jpeg artifacts,signature ,watermark,username,blurry,dim light.
Big models: revAnimated v122, Mai Orange Realistic, 3D Character PLUS_v1.0, this lora generalization is higher, realistic, 3d, illustration class big models can try under.
Big model link: https://www.liblib.art/modelinfo/1004b01e19714137a593e30007f3c737?from=search、https://www.liblib.art/modelinfo/7aafa2f6730f432c8e0111c678fca77d?from=search、https://civitai.com/models/43331/majicmix-realistic
Lora weight: 0.8
Sampling method (sampler): Euler a + Karras (according to the actual situation can choose sampler)
Iteration steps: 24
CFG Scale: 7
Resolution reference: 512*768 is recommended.
High resolution fix (Hires. fix): 1. zoom algorithm: R-ESRGAN 4x+ Anime6B, 2. redraw amplitude: 0.3, 3. zoom speed: 2x