✨ JANKU v4.0 - Trained + NoobAI EPS + RouWei N/SFW Illustrious XL✨ - v4.0 🥇🔥
Wyróżnione obrazy
Zalecane podpowiedzi
lazypos, 1girl
Zalecane negatywne podpowiedzi
lazyneg
Zalecane parametry
samplers
steps
cfg
clip skip
resolution
vae
other models
Wskazówki
Use embeddings for easier and more accurate prompting, including positive, negative, and NSFW embeddings, to improve image quality and save generation costs.
Check image metadata for exact prompts and settings used by the author to reverse-engineer the workflow via tools like ComfyUI.
If eyes appear wonky in generated images, use an eye detailer but it is generally unnecessary unless the subject is distant.
Najważniejsze informacje o wersji
v4.0 Changelog
v4.0 is a checkpoint trained on thousands of images from popular and recent gacha games, primarily miHoYo titles. A100 GPUs were rented for training, as local hardware would take years.
After training, the model was further trained to remove low-quality concepts. By default, outputs are higher quality than without quality tags, and even more detailed with them.
Finally, a simple merge of my JANKU-style LoRA (trained on previous JANKU images) was applied. Merging too much risked losing trained knowledge, so only a small merge was possible.
Compared to v3.0, images are way more detailed (see below on how to adjust). A shift towards anime style while keeping the amazing lighting shades from v3.0.
If you want less details or issues with hands, lower CFG to 3 and/or try scheduler Simple instead of Normal. Onsite gen works better with CFG 3, no clue why. If you use my positive embeddings, get the new lazypos and lazynegfrom the page. lazypos v1.0 is not good for v4.0. lazyneg v3 is optimized for JANKU. v4.0 is so good, you don't really need positive or negative prompts to start with, try "1girl" prompt and nothing else yourself and see the magic! 🔮
👉 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!
Sponsorzy twórcy
✨ 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! 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! 🚀
💖 Support & Share the Magic!
Love these tools? Like, add to collection, and tag this resource in your creations—I’d adore to see what you make! 🎨✨
👉 More goodies on my profile!
✨ 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 v4.0 🌟
✨ Key Features:
🔥 LoRA-Free Workflow: Generate high-quality art without stacking detailers (unless you’re adding niche styles/concepts).
🔞 NSFW Mastery:
Better anatomy (yes, even in complicated poses) + improved male framing.
No more stability issues —generate confidently at 1024x1536 without upscaling .
🎨 Crisp Details: Enhanced backgrounds, outfits, and character features.
👀 Prompt Responsiveness: Gets your vision right the first time (might be intense for some—adjust CFG! ).
🔧 VAE Baked In: No extra steps—just generate.
Read version details 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 here.
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: 30
CFG: 3-5 (I use 5 normally)
Sampler: Euler A (my go-to)
Scheduler: Normal or Simple
Resolution: 1024x1536 (native quality—no upscaling needed!). Standard Illustrious/SDXL resolutions also supported (1024 x 1024, 1152 x 896, 896 x 1152, 1216 x 832, 832 x 1216, 1344 x 768, 768 x 1344, 1536 x 640, 640 x 1536).
Prompting: Use my embeddings for positive and negative and even NSFW embeddings to prevent or add 🙈. No more guessworks for prompting! If you don't want to use embeddings, use your normal NoobAI/Illustrious quality triggers. Artist and booru tag support. Rating tag support.
v4.0 - Download the new lazypos v2.0, don't use the old v1.0 for v4.0!!
Pro Tips
Using embeddings for onsite gen doesn't cost you more 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 patch it fast. This is my main model now, and I’ll keep improving it.
❤️ Why I Made This
Tired of juggling 10 LoRAs for NSFW art? Me too. This checkpoint is my personal playground —designed for creators who want bold, detailed, no-BS generations .
Future updates? Always. Let’s push boundaries together.
Key upgrades:
NSFW-focused tone with playful warnings (🔞, 🚨).
RouWei base merged with brightness and contrast fixed.
Please share your feedback to improve the checkpoint together! ❤️
Szczegóły modelu
Dyskusja
Proszę się log in, aby dodać komentarz.
