Delete archive_illustrious/janku_v3.txt
Browse files- archive_illustrious/janku_v3.txt +0 -105
archive_illustrious/janku_v3.txt
DELETED
|
@@ -1,105 +0,0 @@
|
|
| 1 |
-
Original link: https://civitai.com/models/1277670?modelVersionId=1596786
|
| 2 |
-
|
| 3 |
-
Creator: https://civitai.com/user/janxd
|
| 4 |
-
|
| 5 |
-
About this version:
|
| 6 |
-
v3.0 released!
|
| 7 |
-
|
| 8 |
-
Merged v2.1 with RouWei base. Lots of fixes added to adjust brightness and contrast without prompting! RouWei base has updated knowledge cutoff at Dec 20th 2024.
|
| 9 |
-
|
| 10 |
-
Merged in some blocks from Janku v2.0 and v1.0 to bring back some more anime style.
|
| 11 |
-
|
| 12 |
-
Better shade lightning compared to previous.
|
| 13 |
-
|
| 14 |
-
Brighter colors, less dark.
|
| 15 |
-
|
| 16 |
-
I used new merging strategy that I learned when I worked on Jankun vpred version of the model. Happy to bring this to Janku!
|
| 17 |
-
|
| 18 |
-
✨Improvements from RouWei
|
| 19 |
-
|
| 20 |
-
Easy and versatile prompting with great aesthetic, anatomy, and stability
|
| 21 |
-
|
| 22 |
-
Vibrant colors, smooth gradients, and full brightness range
|
| 23 |
-
|
| 24 |
-
Over 35k artist styles, pure training (no merged weights), and customizable options.
|
| 25 |
-
|
| 26 |
-
Note: you must use by artistname to trigger it!
|
| 27 |
-
|
| 28 |
-
Eliminates watermarks, tag/character bleed, and strange artifacts for better coherence
|
| 29 |
-
|
| 30 |
-
Improved prompt following, stable styles, and accurate artist representation
|
| 31 |
-
|
| 32 |
-
Description:
|
| 33 |
-
💖 Support & Share the Magic!
|
| 34 |
-
Love these tools? Like, add to collection, and tag this resource in your creations—I’d adore to see what you make! 🎨✨
|
| 35 |
-
|
| 36 |
-
👉 More goodies on my profile!
|
| 37 |
-
|
| 38 |
-
✨ Tired of typing prompts + want viral-ready art?
|
| 39 |
-
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)
|
| 40 |
-
|
| 41 |
-
👉 Join me on our discord server! We have CivChan there!
|
| 42 |
-
|
| 43 |
-
👉 Support future updates: Buy me a coffee or tip buzz! Every bit helps. Thank you for fueling the art! 🚀
|
| 44 |
-
|
| 45 |
-
🚨 JANKU v3.0 🌟
|
| 46 |
-
✨ Key Features:
|
| 47 |
-
|
| 48 |
-
🔥 LoRA-Free Workflow: Generate high-quality art without stacking detailers (unless you’re adding niche styles/concepts).
|
| 49 |
-
|
| 50 |
-
🔞 NSFW Mastery:
|
| 51 |
-
|
| 52 |
-
Better anatomy (yes, even in complicated poses) + improved male framing.
|
| 53 |
-
|
| 54 |
-
No more stability issues —generate confidently at 1024x1536 without upscaling .
|
| 55 |
-
|
| 56 |
-
🎨 Crisp Details: Enhanced backgrounds, outfits, and character features.
|
| 57 |
-
|
| 58 |
-
👀 Prompt Responsiveness: Gets your vision right the first time (might be intense for some—adjust CFG! ).
|
| 59 |
-
|
| 60 |
-
🔧 VAE Baked In: No extra steps—just generate.
|
| 61 |
-
|
| 62 |
-
✨Improvements from RouWei
|
| 63 |
-
|
| 64 |
-
Easy and versatile prompting with great aesthetic, anatomy, and stability
|
| 65 |
-
|
| 66 |
-
Vibrant colors, smooth gradients, and full brightness range
|
| 67 |
-
|
| 68 |
-
Over 35k artist styles pure training (no merged weights), and customizable options. The list in .txt can be found here.
|
| 69 |
-
|
| 70 |
-
Note: you must use by artistname to trigger it!
|
| 71 |
-
|
| 72 |
-
Eliminates watermarks, tag/character bleed, and strange artifacts for better coherence
|
| 73 |
-
|
| 74 |
-
Improved prompt following, stable styles, and accurate artist representation
|
| 75 |
-
|
| 76 |
-
🛠️ Recommended Settings
|
| 77 |
-
Steps: 30
|
| 78 |
-
|
| 79 |
-
CFG: 3-5 (I use 5 normally)
|
| 80 |
-
|
| 81 |
-
Sampler: Euler A (my go-to)
|
| 82 |
-
|
| 83 |
-
Resolution: 1024x1536 (native quality—no upscaling needed!). Standard SDXL resolutions also supported.
|
| 84 |
-
|
| 85 |
-
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.
|
| 86 |
-
|
| 87 |
-
Pro Tip: Check my images’ metadata for exact prompts/settings. Import them into ComfyUI to reverse-engineer my workflow!
|
| 88 |
-
|
| 89 |
-
🩺 Fixes & Feedback
|
| 90 |
-
Eyes still wonky? Use eye detailer, but most of the time you don't need unless the subject is further away.
|
| 91 |
-
|
| 92 |
-
Found a bug? Report it—I’ll patch it fast. This is my main model now, and I’ll keep improving it.
|
| 93 |
-
|
| 94 |
-
❤️ Why I Made This
|
| 95 |
-
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 .
|
| 96 |
-
|
| 97 |
-
Future updates? Always. Let’s push boundaries together.
|
| 98 |
-
|
| 99 |
-
Key upgrades:
|
| 100 |
-
|
| 101 |
-
NSFW-focused tone with playful warnings (🔞, 🚨).
|
| 102 |
-
|
| 103 |
-
RouWei base merged with brightness and contrast fixed.
|
| 104 |
-
|
| 105 |
-
Please share your feedback to improve the checkpoint together! ❤️
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|