Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
noosphere_v42.safetensors
1.99 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<noosphere42>
About This Model
STABLE DIFFUSION 1.5 · Base Models
Created by
UMAZTLI
on Civitai
Noosphere by skumerz. V4.2 Still has fantasy elements, less dark, more delicate features, tried to fix some stuff to make it a bit better (different negative embeddings give it different effects so experiment, explore) Just used block merging on older models. Please use adetailer to fix them faces - https://github.com/Bing-su/adetailer I use this for negatives for most images: (worst quality:2), (low quality:2), (normal quality:2), (monochrome), normal quality, lowres, watermark, badhandv4 Or (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, normal quality, ((monochrome)), ((grayscale)), ((text, font, logo, copyright, watermark:1)), easynegative, badhandv4 [or just use whatever you want baby]
Creator notes
Hello thank you for taking an interest in my model ♥ just trying to make a model that makes cool images :) I like dark stuff so it might have some dark elements to it along with fantasy. V4.2 Still has fantasy elements, less dark, more delicate features, tried to fix some stuff to make it a bit better (different negative embeddings give it different effects so experiment, explore) Just used block merging on older models. Please use adetailer to fix them faces - I use this for negatives for most images: (worst quality:2), (low quality:2), (normal quality:2),  (monochrome), normal quality, lowres, watermark, badhandv4 Or  (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, normal quality, ((monochrome)), ((grayscale)), ((text, font, logo, copyright, watermark:1)), easynegative, badhandv4 [or just use whatever you want baby] DPM++2m Karras and DPM++2S a Karras give nice results Pruned version has baked vae, full version does not. _ - If you like my work be sure to support my caffeine addiction 😛___________________________________________________________________________________________ Version4 Finally got something I was happy with, had to do some training to get it the look I was trying to achieve, hope you like it : D Once again it is dark, like my soul. It has dark fantasy and some scifi elements to it. Tools used: I had best results using: (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, (text, font, logo, copyright, watermark), easynegative Badhandv4 - Bad-Hands-5 - Fast Negative Embedding - [ these work too ] EasynegativeV2 - Easynegative - Deep Negative V1.x -   Adetailer - - use to fix up faces, this is a miracle tool ((please use hire.fix to improve quality)) Upscaler - – 4x- UniScaleV2_moderate If necessary be sure to use inpaint after upscaling to polish things up even more, Be sure to use: (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, (text, font, logo, copyright, watermark) [ negative embedding ] - in negative prompt to get similar results _________________________________________________________________________________________ Version3 - tried to make it more realistc, still dark and fantasy stuff :) - Pruned - baked in VAE Tools used: I noticed [TI] EasyNegativeV2 along with Deep Negative can give decent results, so I would definitely recommend to try those out. Those embeddings tone down the saturation. [TI] EasyNegativeV2 - Deep Negative - _________________________________________________________________________________________ Easynegative - badhandv4 - Vae used - baked in Upscaler used - -- 4x-UniScaleV2_moderate ((please use hire.fix to improve quality)) If necessary be sure to use inpaint after upscaling to polish things up even more, __________________________________________________________________________________________ Version 2: Tried to make things a bit better, better faces, a bit more color, and a bit more nsfw support - Pruned - baked in VAE Tools used: vae - baked in upscaler - -- 4x-UniScaleV2_moderate Suggested negative tags: (worst quality, low quality, normal quality:1.7), lowres, normal quality, ((monochrome)), ((grayscale)), ((text, font, logo, copyright, watermark:1.6))
0 downloads · 1,399 likes on Civitai
SHA256
7B59A31ACF791168A6C4258D521B2BA99A06EBE3BE91750EF870641BF3DB59A0
ModelTrends.ai Model ID
#1985
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
Sampler
DPM++ 2M Karras
Steps
25
Guidance
7
Seed
1846946552
Size
512x512
Clip skip
2
Prompt
(fiery eyes:1.2), perfect eyes, detailed eyes, defined eyelashes, almond shape, <lora:add_detail:0.8>
Negative prompt
EasyNegativeV2, (low quality:1.32), (normal quality:1.31), (worst quality:1.33), (bad anatomy), (bad Hands), (mutated limbs:1.2), (mutated hands, mutated fingers:1.2), (deformed hands:1.2), (text:1.5), simple background, watermark, BadDream, UnrealisticDream, pimple, pimples, freckle, freckles, impurities, signature, artist signature, error, censored, bar censor, text, speech bubble, Unspeakable-Horrors-Composition-4v, verybadimagenegative_v1.3
Settings
Sampler
DPM++ 2M Karras
Steps
30
Guidance
16
Seed
455712052
Size
512x768
Prompt
(masterpiece, best quality, ultra-detailed:1.2), 1girl, perfect curves, (g0ld3mb, gold:1.1), (glimmering galaxy dress:1.1), long straight blonde hair, laced hair, wrapped in white silk, (red background:1.2), riding a wolf <lora:tools/epiNoiseoffset_v2> <lora:freckledvixon_gold_leaf_style_v1.0:1:LBW=0,0,0,0,0,0,0,1,1,1,1,1,0,0,0,0,0;>
Negative prompt
(worst quality, low quality, bad quality:1.3), embedding:ng_deepnegative_v1_75t, embedding:EasyNegative, embedding:badhandv4
Settings
Sampler
Restart
Steps
55
Guidance
7
Seed
4255042700
Size
512x768
Clip skip
2
Prompt
Epic CG masterpiece, hdr,dtm, full ha,8K, ultra detailed graphic tension, dynamic poses, stunning colors, 3D rendering, surrealism, cinematic lighting effects, realism, 00 renderer, super realistic, full - body photos, super vista, super wide Angle, HD， In a futuristic abandoned city, a girl with a huge mechanical arm is engaged in a fierce struggle with the enemy, Her name is Alita, a fighting angel from the future world, Her eyes are firm and resolute, showing the desire for victory, high-definition picture, real effect, hyper-realistic portraits, xiaofei yue, uniformly staged images, flat yet expressive, goth， <lora:绪儿-阿丽塔 Alita:0.8>
Negative prompt
(nsfw:1.3), bad-artist，bad-artist-anime，bad-hands-5，bad-image-v2-39000，bad-picture-chill-75v，bad_prompt，bad_prompt_version2，badhandv4，EasyNegative，NG_DeepNegative_V1_75T， (worst quality:2),(low quality:2),(normal quality:2),lowres,watermark, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature,
Settings
Sampler
UniPC
Steps
14
Guidance
7
Seed
1746720977
Size
1248x1824
Prompt
dystopian style of a female angel with wings. Her hair covers part of her beautiful face and upper body. She wears a medieval beige elven hooded coat that reaches down to her knees and is cut off there. (She has large wings extending from her back. The symmetrical wings are menacing, with visible feathers; they are spread wide and fill the upper half of the picture). She stands relaxed between scattered trees on a withered, grassy steppe. The ground is littered with leaves. At golden hour, autumn, autumn leaves. There is a misty or smoky atmosphere around the figure, giving the picture a mystical element. The picture is in a monochromatic scheme, mainly with shades of black, white and gray. dystopian, highly detailed, bleak, post-apocalyptic, somber, dramatic
Negative prompt
ugly, deformed, low contrast, low quality, low detailed, vibrant, colorful, optimistic, cheerful, ordinary, mundane
Settings
Sampler
DPM++ 3M SDE Karras
Steps
90
Guidance
3
Seed
3285358074
Size
512x768
Clip skip
2
Prompt
RAW photo,award winning photo,(masterpiece:1.3),(best quality,ultra detailed,intricate),professional photography,professional lighting,HDR,High Dynamic Range,(((photo realistic,ultra realistic,photorealistic,8k uhd))),beautiful and aesthetic, ,female samurai posing with sword,sitting,kimono covers only half her body,almost naked,arm wraps,<lora:anxiang:0.8>,
Negative prompt
(worst quality:2,low quality:2),SkinPerfection_NegV15,BadDream,UnrealisticDream,dangercrow,dangerdonkey,dangerhawk,dangermouse,verybadimagenegative_v1.3,fcNeg-neg,art,cartoon,anime,AS-Adult-neg,bad-hands-5,negative_hand-neg,boring_e621_v4, ,(extra fingers, deformed hands, polydactyl:1.2),bhands-neg,
Settings
Sampler
UniPC
Steps
14
Guidance
7
Seed
1746720977
Size
1248x1824
Prompt
dystopian style of a female angel with wings. Her hair covers part of her beautiful face and upper body. She wears a medieval beige elven hooded coat that reaches down to her knees and is cut off there. (She has large wings extending from her back. The symmetrical wings are menacing, with visible feathers; they are spread wide and fill the upper half of the picture). She stands relaxed between scattered trees on a withered, grassy steppe. The ground is littered with leaves. At golden hour, autumn, autumn leaves. There is a misty or smoky atmosphere around the figure, giving the picture a mystical element. The picture is in a monochromatic scheme, mainly with shades of black, white and gray. dystopian, highly detailed, bleak, post-apocalyptic, somber, dramatic
Negative prompt
ugly, deformed, low contrast, low quality, low detailed, vibrant, colorful, optimistic, cheerful, ordinary, mundane
Settings
Sampler
DPM++ 2M Karras
Steps
26
Guidance
7.5
Seed
4205969523
Size
512x768
Clip skip
2
Prompt
(looking at viewer:1.2), BREAK, (1girl:1.2), (solo:1.0), (sitting:1.0), (large breasts:1.0), (blush:1.0), (smile:1.0), (pink hair:1.2), (thighhighs:1.0), (red ribbon:1.0), (hair ornament:1.0), (cleavage:1.0), (bare shoulders:1.1), (twintails:1.2), (sitting:1.0), (collarbone:1.1), (microskirt:1.0), (head tilt:1.0), (egirl clothes:1.0), <lora:eGirlMakeup-10:0.8> EGirlMakeup, <lora:eGirlMakeup-08:0.8>, BREAK, (masterpiece:1.4), (beautiful and aesthetic:1.4) <lora:hair_length_slider_v1:5>
Negative prompt
(worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, normal quality, ((monochrome)), ((grayscale)), ((text, font, logo, copyright, watermark:1)), easynegative, badhandv4, BREAK, (empty background:2.0), (pussy:1.5),
AI Models for Image, Video & Text Generation
noosphere42 is a base model for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models