Run Locally
fnEVONoobXL_v20.safetensors
6.46 GB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Creator notes
工作流下载 | Download Workflow
-
模型介绍 | Introduction:
-
基于未公开的V10版本及个人训练中的V-pred模型,融合多个个人训练LoRa调整而成的产物。当前所有测试皆基于Comfyui,未在Webui中测试。
A product formed by integrating multiple personal training LoRas based on the unpublicized V10 version of and the V-pred model in personal training. All current tests are based on Comfyui and have not been tested in Webui.
-
在训练及调整V-pred模型途中,偶然发现与E-pred模型可在部分层中融合,并具有更加优秀的效果,决定并以E-pred作为底模类型进行融合调整。因融合多个画师LoRa导致部分画师tag效果不如原版Fn-Mix Noob XL明显,但除此之外在画面表现力、背景、人物细节等方面都有较大提升。
During the training and adjustment of the V-pred model, it was accidentally discovered that it could be integrated with the E-pred model in some layers, resulting in even better performance. Therefore, it was decided to use the E-pred model as the base model type for integration and adjustment. Due to the integration of multiple artists' LoRas, the effects of some artist tags are not as obvious as the original Fn-Mix Noob XL. However, aside from this, there have been significant improvements in aspects such as the expressiveness of the images, backgrounds, and character details.
-
Fn-Mix Noob XL及Fn-Evo Noob XL系列的目标:做好基础效果,并兼容更多画师风格,搭配多个不同画师tag获得独特画风。希望各位可以在使用该模型创作时也多尝试组合使用各类画师tag,获得更多的画风以及乐趣。如果你喜欢这系列模型,请点个赞,这对我是很大的鼓励。
The goals of the Fn-Mix Noob XL and Fn-Evo Noob XL series: achieve good basic effects, be compatible with more styles, and obtain unique painting styles by combining multiple artist tags. I also hope that everyone can try to combine various artist tags when using this model for creation to obtain more styles and have more fun. If you like this series of models, please give a thumbs up. It would be a great encouragement to me.
参数推荐 | Recommend:
-
Resolution:832*1536/1024*1536/768*1344/832*1216
-
Postive prompt:
style/artist tags + your prompt + masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest
-
Negative prompt:
lowres, worst quality, bad quality, bad hands, bad feet,
-
a1111_prompt_style: false
-
Steps: 25
-
CFG: 4-5
-
Sampler: euler_ancestral/euler
-
Scheduler: karras/nomal
-
Hires Fix Step: 4
-
Hires Fix CFG: 2
-
Hires Fix Sample: euler_ancestral/euler
-
Hires Fix Scheduler: karras/nomal
-
Hires Fix Denoise: 0.2
推荐风格/画师 | Recommend style/artist tags:
1.0:
-
(dizi930:1.25), imamura ryou, (reoen:0.75)
-
(yoneyama mai:0.85), (hiro \(dismaless\):0.95)
-
itefu, (tatsumi \(psmhbpiuczn\):0.75), (nixeu:0), yoneyama mai, realistic
-
redum4
2.0:
-
imamura ryou, redum4, reoen, (popqn:0.75)
-
imamura ryou,redum4,hiro \(dismaless\),ohisashiburi,jaggy lines
-
(redum4:1),(hiro \(dismaless\):0.95),(ohisashiburi:1.05),(ran'ou \(tamago no kimi\):0.875)
-
souji hougu, range murata, reoen
SHA256
16422963F4E103C426CA9A2F5889247AC872E609A82237492872F5F9CF7F8A8C
ModelTrends.ai Model ID
#20580
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
1248x2016
Prompt
imamura ryou, redum4, reoen, (popqn:0.75), 1girl, dynamic angle, dutch angle, on stomach, head tilt, head rest, animal ears, blonde hair, eyes visible through hair, frilled hairband, frilled skirt, grass, green eyes, green hairband, legs up, long hair, long sleeves, looking at viewer, lying, multicolored hair, multiple tails, neck ribbon, official alternate costume, outdoors, plant, red ribbon, ribbon-trimmed skirt, smile, solo, streaked hair, white flower, white pantyhose, white tail, yellow tail, light particles, bloom, depth of field
Settings
Sampler
Euler a
Steps
28
Guidance
4.5
Seed
112508681802367
Size
1664x2432
Prompt
imamura ryou, redum4, reoen, (popqn:0.75),
1girl,sheep girl,furry female, kemono, body fur,taur,smile,frilled shirt,waitress,fluffy, silver hair,forehead,wavy hair,light pink uniform,(maid:0.6),short hair,holding tray,under-rim eyewear,cafe,medium breasts,
masterpiece, best quality, amazing quality, very aesthetic, absurdres, newest
Negative prompt
worst quality, low quality, normal quality, lowres, bad anatomy, bad hands, signature, watermarks, ugly, imperfect eyes, unnatural face, unnatural body, error, extra limb, missing limbs,
Similar Models
AI Models for Image, Video & Text Generation
fn evonoob xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
More Stable Diffusion XL 1.0 modelsMore Stable Diffusion XL 1.0 Base Modelsillustriousanimebasestyle
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
