Hi! Here's a quick introduction to the model:
You probably don't want to read it all, do you? In short, with 14 steps (6 buzz), you already have a quality image~
PS: This version should be quite compatible with SDXL based loras (PDXL, NOOBAI, IL).
----------------------------------
📦 UtopiaXL V3.0
So, I’ve been testing Utopia v2, and while it was great for concepts and poses, the base style sometimes broke if you didn’t use quality prompts. (Honestly, it was pretty random unless you added an artist tag—but when you did, it worked quite well.)
Anyway… this version represents several days of work, over a dozen revisions… and many restarts (not that I’m complaining 😅).
At first, my plan was to continue building on ILv0.1. I even created a lighter 2.5 version (less than 5 GB, nearly 4), which was aimed at cleaning up some issues.
It worked well, but I wasn’t sure if removing certain data would break it further if I planned to update it again. So, after a lot of trial and error, I got tired and… decided to start from scratch.
This time, I started from ILv2.0, merging NoobAI and all the models I had previously used—plus some new ones (I’m sorry, I don’t have a full list). Of course, I included the key data from earlier versions and added new concepts, characters, and styles. My goal was to make it as compatible and adaptable as possible, so I refined a lot of things to avoid the usual errors from the previous version—like glitches when not using styles or quality triggers such as anime, cartoon, shiny, or shiny skin, or when missing recommended negatives.
I also fixed conceptual styles like pixel art, realism, 3D, PVC, and semi-realism, which barely worked before.
In short, AGGA’s Utopia is now optimized enough to generate detailed illustrations in 15 steps or less. It’s versatile, flexible, and much more consistent… exactly what I was aiming for.
I would’ve loved to add even more content, like additional VTubers or alternate versions of certain characters, but the submission deadline was getting close, so I chose to release it now.
If everything goes well, this should be the final version of the project. There’s a lot I set aside—maybe it’ll see the light in a future model (waaay in the future).
I hope you enjoy using it as much as I enjoyed creating it! See you ~ (´･з･)/
----------------------------------
⚙️ Optimal Settings Guide
Designed for flexibility and quality across multiple styles.
🧭 Steps: 14–28 Efficient results from 10+ steps. Best quality around 20–24.
🎯 CFG Scale: 3.5 – 7 Try 4.5 for flexible results or 5.5 for sharper definition.
📈 Samplers: DPM++ 2M Karras, Euler a, DPM++ SDE Works well with most modern samplers. Choose what fits your style.
🖼️ Recommended Resolution:
Start from 1024x1024 or larger for better structure and detail. Model scales well to 1536x896, 1152x1344, and portrait/landscape layouts.
🔁 Upscaling Recommendations
To retain fine detail while boosting resolution:
Upscaler: R-ESRGAN 4x+ Anime6B / 4x-UltraSharp
Denoising strength: 0.35 – 0.5
Steps (if re-rendered): 20
Scale: 1.4 – 2.0
🧬 VAE Support
Note: The model already includes an internal VAE — no need to load an external one.
🛡️ Content Labeling
This model can produce content across categories. Ensure you mark your generations responsibly:
General / Artistic / Sensitive / NSFW / Explicit
To reduce undesired ***** content, add "nsfw" or "explicit" to the negative prompt.
----------------------------------
🏷️ Prompting Tips
🔹 Positive Prompts:
sexy_perspective, (masterpiece), (best quality), (ultra-detailed), amazing quality, very aesthetic, illustration, perfect composition, intricate details, absurdres, incredibly absurdres, shiny skin, shiny hair, clear skin, ultra-detailed-eyes, greatscore, extreme perspective, dynamic angle, dynamic pose
Optional Enhancers:
Others More: anime, cartoon, shiny skin, shinym slutty, sexy, slut:2.1, cute, eyelashes,
pretty, Creepy, watercolor, abstract, dark theme
shiny skin, abstract elements, glowing effect, magical aura, intense gaze, cinematic background, surreal scenery, high realism
anime style, cartoon, soft shading, detailed skin, stunning eyes, dynamic lighting, best quality, masterpiece, intricate detail, expressive face, dramatic pose, cinematic lighting, depth of field, amazing composition, elegant design, vibrant colors
🔸 Negative Prompts:
bad quality,worst quality,worst detail,sketch,censor, low quality, anatomical nonsense, bad anatomy, lowres, normal quality, worst aesthetic, ugly, mismatched pupils, dirty face, extra limbs, bad hands, bad fingers, watermark, artist name, signature, text, patreon username, patreon logo, web address, email address,
Others More:
low quality, bad anatomy, blurry, distorted face, messy hands, long neck, censored, multiple pupils, duplicate limbs, cropped, extra fingers, overexposed, boring composition
----------------------------------
📦 UtopiaXL V2.0
This version includes a bigger number of concepts and tries to rescue some styles that were lost in the previous version (I only added 200 styles since I'm not sure how many illustrious base includes), the ones I've tested work well so there aren't many problems there, it should also include the concepts I added below, but I'm still testing the model to see how many were merged, if it's as I expect, there should be more than 200 concepts (although I only added them to make my life easier, in short... I hope you like it~)
⚙️ Recommended Settings:
Steps: 15–30
CFG Scale: 2.5–7 (4.4 or 5.5 recomended).
Sampler: Euler a, DPM++ 2M, etc.
Resolution: Larger than 1024x1024 to take advantage of its original resolution.
Recommendation:
• Clip Skip 1 | CFG 4.5–6 | Greater accuracy in anatomy and clothing, less clutter | Fine-tuning, details, bug fixes.
• Clip Skip 1 | CFG 5.5–7 | Balanced between detail and stylized expression | General use, complex prompts.
• Clip Skip 2 | CFG 4–6 | Smoothed, sometimes dull, less expression | Stability on heavy models.
• Clip Skip 2 | CFG 3.5–7 | Strong style, more saturation or deformations | Artistic effects, exaggerated style.
PS: Try Clip Skip 1 + low CFG (4–6) if you're looking for precision.
PS: Use Clip Skip 2 + higher CFG (4–7) if you're looking for more style or artistic effects.
Recommended Upscaling:
• Scale: 1.5
• Steps: 20
• Upscaler: R-ESRGAN 4x+ Anime6B
• Denoising strength: 0.35 – 0.5
📌 Note: The VAE is already integrated; no need to load an external one.
🛡️ Safety Labels
This model may generate content of various types. Users are expected to correctly categorize its use into the following categories:
General / Sensitive / NSFW / Explicit
Please consciously add "NSFW" to negative labels if you wish to avoid explicit content.
🏷️ Prompt Tips
Positive Prompt:
sexy_perspective, (masterpiece), (best quality), (ultra-detailed), amazing quality, very aesthetic, illustration, perfect composition, intricate details, absurdres, incredibly absurdres, shiny skin, realistic,
Others More: anime, cartoon, shiny skin, shiny, slutty, sexy, slut:2.1, dynamic angle, dynamic pose, dark_art_style, abstract element, abstract background, foreshortening, extreme perspective, high resolution, ultra-detailed, extremely detailed eyes, detailed face, newest, best illumination, depth of field, complex background, detailed background
Negative Prompt:
worst quality, old, early, low quality, lowres, signature, username, logo, bad hands, mutated hands, artist name, sketch, , watermark, logo, patreon username, bad details
----------------------------------
📦 UtopiaXL V1.5
This version reduces the strength of the base style and adds some details, it doesn't change much, it makes it easier to see some perspectives.
Things to keep in mind with this version:
Don't use this model with cutelatte, as this model includes 200% of that data, and that would break the entire model by forcing overfitting, even though it was reduced in version 1.5 (it makes it look unfinished like a scribble). Simply use the descender to force its appearance.
My idea with this is to include several of my loras so the next version will have a larger flow of data in terms of poses or concepts. I'm still not sure whether to use it as a base or clean up some of the folders, or change the base model by going back to Illustrious 0.1
⚙️ Recommended Settings:
Steps: 15–30
CFG Scale: 2.5–7 (4.5 or 5.5 recomended).
Sampler: Euler a, DPM++ 2M, etc.
Resolution: Larger than 1024x1024 to take advantage of its original resolution.
Recommended Upscaling:
• Scale: 1.5
• Steps: 20
• Upscaler: R-ESRGAN 4x+ Anime6B
• Denoising strength: 0.35 – 0.5
📌 Note: The VAE is already integrated; no need to load an external one.
🛡️ Safety Labels
This model may generate content of various types. Users are expected to correctly categorize its use into the following categories:
General / Sensitive / NSFW / Explicit
Please consciously add "NSFW" to negative labels if you wish to avoid explicit content.
🏷️ Prompt Tips
Positive Prompt:
anime, cartoon, shiny skin, shiny, masterpiece, best quality, amazing quality, very aesthetic, high resolution, ultra-detailed, extremely detailed eyes, detailed face, absurdres, newest, best illumination, depth of field, complex background, detailed background
Others More: slutty, sexy, slut:2.1, dynamic angle, dynamic pose, dark_art_style, abstract element, abstract background, foreshortening, extreme perspective,
Negative Prompt:
bad quality,worst quality,worst detail,sketch,censor, big nose, bad anatomy, ugly, worst aesthetic, old, mismatched pupils, dirty face, extra limbs, bad hands, bad fingers