✨ Tired of typing prompts + want viral-ready art?
Pair Lazy Embeddings 🛋️⚡ (zero-typing magic for all models ) with TrendCraft 🪄🚀 (30-day trend-trained detailer ) for effortless masterpieces. Check them out: Lazy Embeddings + Trendcraft (Pony XL , Illustrious , Noob Vpred, or SDXL base trained version)
👉 Join me on our discord server (https://discord.gg/tWrKk3jcXx)! Share art, ask for help, or just chat. We have CivChan bot plus games there!
👉 Support future updates: Buy me a coffee or tip buzz! Every bit helps. Thank you for fueling the art! 🚀
🚨 JANKU 🌟
✨ Key Features:
🔥 LoRA-Free Workflow: Generate high-quality art without stacking detailers (unless you’re adding niche styles/concepts).
🔞
𝐍𝐒𝐅𝐖Mastery:Better anatomy (yes, even in complicated poses) + improved male framing.
𝐍𝐒𝐅𝐖: if you want more control, put lazy𝐍𝐒𝐅𝐖in negative!
Large character list support: Character list shared in our discord server.
No more stability issues —generate confidently at 1536x1536 without up-scaling. My personal resolution to use is 1024 x 1536.
🎨 Crisp Details: Enhanced backgrounds, outfits, and character features.
👀 Prompt Responsiveness: Gets your vision right the first time!
🔧 VAE Baked In: No extra steps—just generate.
Read version details for the version you are using for more information!
✨Improvements from RouWei
Easy and versatile prompting with great aesthetic, anatomy, and stability
Vibrant colors, smooth gradients, and full brightness range
Over 35k artist styles pure training (no merged weights), and customizable options. The list in .txt can be found on our discord server.
Note: you must use
by artistnameto trigger it!
Eliminates watermarks, tag/character bleed, and strange artifacts for better coherence
Improved prompt following, stable styles, and accurate artist representation
🛠️ Recommended Settings
Steps: 25-30 (I use 30 normally)
CFG: 3-5 (I use 5 normally)
Sampler: Euler / Euler A (my go-to)
Scheduler: Normal or Simple (my go-to) or SGM UNIFORM
Model Recommended Resolution:768X1344 832X1216 768X1280 704X1408 1024X1536 (my go-to, no need for up-scaling!)Standard Illustrious & SDXL resolutions also supported
Prompting: Use my Lazy Embeddings for positive and negative and even 𝐍𝐒𝐅𝐖embeddings to prevent or add 🙈. Use lazywet to remove wet and shiny skin. No more guessworks for prompting! If you don't want to use embeddings, use your normal NoobAI/Illustrious quality triggers. There is artist, danbooru, and rating tag support.
Positive promptlazypos {character tags} {detail tags related to character} {background tags}lazypos, 1girl, makima \(chainsaw man\), yandere stare, smile, dress shirt, grey jacket, red hair, sidelocks, black necktie, looking at viewer, jacket, long sleeves, upper body, suit, necktie, shirt, simple background, medium hair, collared shirt, ringed eyes, shaded face, braided ponytail, head tilt, braid, white background, formal, yellow eyes, holding own arm, wing collar, closed mouth, solo
Negative promptlazyneg
Pro Tips
Using my Lazy Embeddings for onsite gen doesn't cost you extra buzz, if anything it helps you save buzz since you're not generating bad images!
Check my images’ metadata for exact prompts/settings. Import them into ComfyUI to reverse-engineer my workflow!
🩺 Fixes & Feedback
Eyes still wonky? Use eye detailer, but most of the time you don't need unless the subject is further away.
Found a bug? Report it—I’ll fix it in next version. I only generate with this model, so I’ll keep improving it. I won't publish something I won't use myself.
❤️ Why I Made This
Tired of juggling 10 LoRAs for 𝐍𝐒𝐅𝐖 art? Me too. I want a 𝐍𝐒𝐅𝐖 checkpoint with more knowledge of characters and other common booru tags. This checkpoint is my personal playground —designed for creators who want bold, detailed, no-BS generations.
Future updates? Always. Let’s push boundaries together.
Please share your feedback to improve the checkpoint together! ❤️
JANKU Checkpoint License & Terms of Service
Comply with the NoobAI-XL 1.0 License
User Responsibility :
You are fully liable for all outputs. Use prompts to filter content.
Restrictions :
No redistribution of modified versions without adhering to open-source terms.
No use for unlawful or harmful purposes.
Failure to comply voids usage rights.
Description
FAQ
Comments (32)
Don't forget to like, comment and share your generated pictures!
May you share the loras you have included and how you merge them? a tutorial or something? I have 100 of loras to use, so thinking to merge them so may you please share?
@krigeta I do not recommend to merge 100 loras unless you plan to always use them like that forever. I also don't think you have enough vram to do 100 at a time, so this process will take a long time. There is an option for you to merge just the loras please see this article: https://civitai.com/articles/10830/merging-loras-with-cgem156-in-comfyui The process to merge checkpoints and loras is the same once you understand the concept.
As for which loras I use, I can't provide the whole list but it is the loras I used in all my images plus popular ones on civitai. There are also some loras I used that isn't shared publicly. Sorry!
@janxd then how can one able to use them using this checkpoint? this checkpoint is more of a personal one then, right?
@krigeta The checkpoint only have generic loras merged in that will help improve the picture. You don't need to select the same loras cause this checkpoint already has it. You can use this checkpoint with other loras in your workflow no problem. Are you trying to use 100 different loras? You can use the lora stack node to do that. Maybe I don't understand your question, please let me know exactly you want to do! I will try my best to help!
"No need to upscale can go generate higher resolution. I don't use upscalers in any of my pictures." Up to what resolution can i got with this Merge? i see your images are 1024x1536 so is 2560 in total the max i can push?
If you have higher vram, you can go a little higher than 1024x1536. But that is my cap for my card if I go any higher it will go oom and crash. Please test and let me know how high you can go without any artifacts if you have a high end gpu! If you want full 4k image, not possible sorry if this is confusing.
I updated my description to be more clear!
I like euler a normal 25 steps and 3 cfg, check my images from today to see example!
Is it based on IL 0.1 or 1.0?
Noob EPS is based on IL 0.1 but it has a ton of fine-tuning done by the community. IMO noob's finetuned checkpoints are way better than what IL 1.0 added.
I admit I barely understand how comfyui and custom nodes work, I just download whatever the manager tells me to do. For some reason I am having issues with
ComfyUI-SaveImageWithMetaData and ComfyUI-ImageMetadataExtension. It keeps saying import failed.
@nl96 I will try to help, the first thing I recommend you to do is get this: https://github.com/ltdrdata/ComfyUI-Manager Once you get this and restart comfyui, you will see Manager in top right. Click that then click install missing nodes. From now on, if you import any workflow with nodes in red outline, do the install missing nodes. Let me know how that goes!
Also if that is hard, you can replace the save image with meta data nodes with regular ones. But if you don't understand node connection, this will be harder.
@janxd There in lies the issue, I am using manager! and its giving me all sorts of weird text about conflicted nodes and modules not found, and no matter how many times I switch versions or re-enable or disable, nothing changes. Oh well I guess I will use the workflow I currently have.
Absolutely loving this model so far. I'll post some images tomorrow, so far the only issue I'm having is the eyes which can usually be fixed with a detailer.
One of my goal with this checkpoint was to fix bad eyes. I will research and try to make a better version. Thank you for the feedback and can't wait to see your creations!
Also try using "blank eyes" in the negative, most of my images use that as a negative.
In fairness, the eyes do generate quite well. Better than most models I've tried. I'm usually quite particular about them is all. I'm going to experiment with backgrounds and landscapes a bit more next 😁
Hi all! Thanks for all the support so far! I'm so happy that people enjoy the model! Don't forget to like and share feedback along with pictures. I already have some adjustments planned for this checkpoint, but it might not happen right away since my checkpoint doesn't have onsite generation :( so I get no buzz earning for this model compared to my LORA works. I do plan to drop an alpha Pony XL + Noob merge next week. Thank you all again!
Ran out of pins! Thanks everybody for sharing! I will try to keep the newer images I like more pinned to the top. Very hard to beat the images coming out from @Tozi_White!
Change back to recommending resmultistep kl_optimal 30 steps 5.5 cfg. 1024 x 1536 resolution ideal you can swap to 1536 x 1024.
I uploaded some new images with those and I also uploaded some pictures of using detailer after for eyes, but honestly it is not that big difference to me. If you want perfection, check out the workflow. The image with the bigger eye mole is before the detailer. https://civitai.com/posts/13407632
Here is another one: https://civitai.com/posts/13408050 this one you can tell the detailer was used for the eyes.
you can adjust the detailer size to just aim for the eyes better
Why your model output same to wai-nsfw-il-v10?
I noticed a picture shared below comparing them. I will check what happened and upload a corrected version.
I found the issue, it is related to the prune node I added after the merge checkpoints step. For some reason, it only saves one checkpoint part of the flow. That's why people that downloaded the the version before 3 days ago didn't see this. I will reupload a corrected version.
Found issue with the new merge workflow I was using where it was saving the first checkpoint as the final. If you download my model in the last 3 days, please delete and don't use as that is not merged correctly. If you download my model since release, you have my intended version and you are fine. I try to figure out the issue by tonight and reupload! Thank you all and sorry to the people looking to download!
Fixed version is uploaded and you will know you have the right version if the file name has fixed at the end.
Any chance of getting this able to use on this site? My pc can't run even comfyui....
@drdahliarose69394 Please use the tensor art link to use the model for free. I can't do anything about Civit because there is limited slots. Hope one day you get a powerful computer to run Comfyui!
@drdahliarose69394 civit added onsite gen! also released a new version - let me know!
on site gen for this model every week!
Details
Files
JANKUTrainedChenkinNoobai_v10.safetensors
Mirrors
jankuV30NoobaiEPSRouwei_v10.safetensors
jankuV30NoobaiEPS_v10.safetensors
jankuV21Illustrious_v10.safetensors
JANKUV40TrainedNoobaiEPS_v10.safetensors
JANKUV4NSFWTrainedNoobaiEPS_v10.safetensors
jankuV2Illustrious_v10.safetensors
JANKUV40NSFWTrainedNoobai_v10.safetensors
JANKUV30NoobaiEPSRouwei_v10.safetensors
JANKUTrainedNoobaiRouwei_v10.safetensors
JANKUV5NSFWTrainedNoobai_v10.safetensors
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.





