( Not my Model )
https://civitai.com/models/1045588?modelVersionId=1945718
For anime style ,use "Sampler-Euler a" and generate high-quality images in 16 steps.
--
For realistic style, use "Sampler-Euler a" and generate high-quality images in 18 steps.
--
This version can switch between realistic style and anime style.
This version can use realistic or anime style lora.
Can use sdxl and lora of Illustrious.This version can also use parts of the "pony" lora.
---
Ways to make your cosplay character's face more realistic:
Lower the role's weight，frieren → (frieren:0.8)
--
If the effect of training some lora in my checkpoint is not good, you can train lora in " noobaiXLNAIXL_epsilonPred11Version " or “ illustriousXL_v01 ", so that lora is still available in my checkpoint.
--
Sliders lora for color temperature, brightness, saturation, and contrast.
--
You can use PornMaster-Pro-SDXL-V4 or other realistic checkpoints as a "Refiner" to increase realism. (Pruned version of fp16 is faster.)
You can also use PornMaster-Realism-IL-V1 , BigAspV2 or CyberIllustrious as a refiner.
--
Add details and improve the accuracy of prompt words lora.
--
--
NoobAI-XL ControlNet-OPENPOSE.
--
My other checkpoints and Lora.
--
sd-webui-regional-prompter <<<<<
--
Light and color control: sd-channel-offset
--
"If you want to post your work on my model, you can upload up to 20 images in a single post. If the work is outstanding, I can feature it at the top of the displayed images."
--
(Realistic style)
(positive prompt):
realistic,photorealistic,masterpiece,best quality,newest,highres,absurdres,photo, cosplay photo,photo \(medium\), dslr, real life, real life insert, real world location, photo background
( negative prompt):
lowres, worst aesthetic, bad quality, worst quality, bad anatomy, jpeg artifacts, scan artifacts, lossy-lossless, unfinished, ugly, poorly drawn, greyscale, (illustration, 2d, 2.5D, 3d, painting \(medium\), toon \(style\), sketch, comic, anime,flat color,outline,smooth skin:1.2) watermark, text, extra digits
--
(Anime style)
(positive prompt):
very awa,masterpiece,best quality,year 2024,newest,highres,absurdres,anime, anime coloring
( negative prompt):
(realistic,photorealistic,photo:1.2),lowres,worst aesthetic,bad quality,worst quality,bad anatomy,sketch,jpeg artifacts,scan artifacts,lossy-lossless,ugly,poorly drawn,signature,watermark,greyscale,ai-generated, photo \(medium\),real life, real life insert, real world location, photo background
--
Adhere to the Fair AI Public License , ensuring that any derivative works are also open source.
--
--
Preview images & prompts for 20,000+ Danbooru Characters:
https://www.downloadmost.com/NoobAI-XL/danbooru-character/
Preview images & tags for 6,000+ Danbooru Artists' styles:
https://www.downloadmost.com/NoobAI-XL/danbooru-artist/
Preview images & tags for 4,000+ e261 Artists' styles:
https://www.downloadmost.com/NoobAI-XL/e621-artist/
Preview images & tags for 3,000+ e621 Characters:
https://www.downloadmost.com/NoobAI-XL/e621-character/
--
Easy to use:
Go to " Danbooru " or " e621 " to select a picture, copy all the prompt words in the picture, and then enter the prompt words, or add commas to spaces and remove underscores.
--
AUTOMATIC1111:
Check "Clip skip SDXL" in the settings to enable the Clip function.
ENSD:31337
(ENSD; does not improve anything, just produces different results for ancestral samplers - only useful for reproducing images)
--
(Reverse prompt word tool):" JoyCaption Alpha One "
--
Better results are achieved when using natural language and mixing in " danbooru " tags.
--
Always show all networks on the Lora page(otherwise, those detected as for incompatible version of Stable Diffusion will be hidden)
--
If you like my model, you can encourage me with "buzz".
---
I only publish my models and lora in " civitai " and " seaart ", all other places are plagiarism.
--
Customized lora: My Telegram ID: @iamddtla0620
My WeChat ID: iamddtla
My Line ID: iamddtla
Time is precious, please state your intention directly, for example: customized LORA.
--
For partial facial redrawing, adetailer or sd-face-editor can be used.
High resolution upscaling can be done using " ultimate SD upscale ".