Creating people who create! We are AICU media from Japan!
A new version, Animagine XL 3.1, has been released from the image generation model ‘Animagine XL 3.0’, which was published on January 16, 2024 based on Stable Diffusion XL (SDXL)!
This article will compare the differences in visual style and other aspects between Animagine XL 3.0 and Animagine XL 3.1, as well as introduce the new tags introduced from Animagine XL 3.1.
Which Model is Suitable for Manga Production? I Conducted a Detailed Comparison of Animagine 3.1 vs. Animagine 3.0!
In Animagine XL 3.1, you can continue using the important prompts that were available in Animagine XL 3.0!
Here are the release notes for Animagine XL 3.0.
Here is Hugging Face.
Official Release(Parcial Excerpt）
Animagine XL 3.1 is an enhancement over the previous version, Animagine XL 3.0, designed to generate anime-style images of higher quality. It includes a wider range of characters from famous anime series, optimized datasets, and new tags for better image creation. Aimed at providing valuable resources for anime fans, artists, and content creators through accurate and detailed representation of anime characters.
That is, “Animagine XL 3.0 has been improved for higher quality!”
Now, let’s compare with Animagine XL 3.0.The environment used for this generation was a GALLERIA laptop with Windows 10, equipped with NVIDIA GeForce RTX 3060 with 6GB VRAM, directly installed with ComfyUI.
Initially, generate using a simple prompt and compare it with Animagine XL 3.0.
Prompt : best quality, 1girl
Negative Prompt : worst quality, low quality, normal quality, bad anatomy, NSFW
The significant features such as a strong light source,a hairstyle with visible ears, and a sense of backlight remain unchanged. However, distinctive features of Animagine XL 3.0, such as slanted eyes and pink cheeks, are less prominent now, and the overall exposure has been reduced. Also, while Animagine XL 3.0 had a glossy skin tone, that too has been toned down, resulting in a more subdued overall appearance.
Additionally, compared to Animagine XL 3.0, Animagine XL 3.1 has clearer and finer line art, with reduced thickness and depth, giving a slightly more two-dimensional impression.
In Animagine XL 3.0, there were “era tags” to specify the art style and “quality tags” to indicate the quality level. In Animagine XL 3.1, in addition to updates to these tags, “Aesthetic Tags” have been added.
The numerical values of the traditional quality tags have been slightly adjusted, and some tag names have been changed. However, commonly used tags like “masterpiece” and “best / worst / low quality” remain unchanged, so they can still be used in the same way as before.
The main changes include the addition of “2024” and slight adjustments to the years, and the change of “late” to “recent”. The era tags have not changed significantly.
Images similar to Animagine XL 3.0.
It has a slightly refined atmosphere compared to the newest version. It’s the heyday of VTubers, isn’t it?
The decadent atmosphere is cute. The art style has clearly moved away from the VTuber style.
It has a sepia-toned atmosphere.
It’s the era when Haruhi Suzumiya and Yuki Nagato were popular. There’s a taste of the 90s style, and the distinction in artistic approach is clearly noticeable.
The rating tags used to adjust sensitive content haven’t changed significantly from Animagine XL 3.0. Use prompts and negative prompts selectively to adjust the exposure level.
It’s a tag used to generate visually appealing content using a ViT (Vision Transformer) image classification model specialized in anime data, along with the model shadowlilac/aesthetic-shadow-v2, which evaluates the aesthetic value of content.
The prompt “best quality, 1girl, very aesthetic”
The camera angles and poses have become more dynamic!
The ‘aesthetic’ prompt works effectively on platforms like Nijijourney and Novel AI, so give it a try!
I will introduce recommended settings and prompts as presented on the official Hugging Face platform.
‘Absurdres’ is a term coined from ‘absurd resolution,’ meaning an incredibly high resolution.
masterpiece, best quality, very aesthetic, absurdres
nsfw, lowres, (bad), text, error, fewer, extra, missing, worst quality, jpeg artifacts, low quality, watermark, unfinished, displeasing, oldest, early, chromatic aberration, signature, extra digits, artistic error, username, scan, [abstract]
Low（5–7）
30 or fewer
Euler a（Euler Ancestral）
These are my favorite generated images!
Koto-chan
Oldest
Newest
Anime style
Feel free to share your favorite generated images once you’ve created them!
❏Members-only image posting corner
https://note.com/aicu/membership/boards
https://note.com/aicu/membership/boards/61ab0aa9374e/posts/17273820a798
Recommended prompts for Animagine XL 3.0 are as follows.
❏ANIMAGINE XL 3.0: Transforming Art Styles! Recommended Prompt Collection
https://note.com/aicu/n/n44085d702617
❏Introduction to Stable Diffusion — ControlNet can be found here.
https://note.com/aicu/n/nde6fe41f077b
❏Beginner’s series on img2img is available here.
https://note.com/aicu/n/n08ebe0637a41
Below, I provided a link to ‘AUTOMATIC1111/Stable Diffusion WebUI’ that runs on Google Colab.
https://note.com/aicu/membership/boards/61ab0aa9374e/posts/7cab00942b22?from=self
Here is the support bulletin board for members! Your support is greatly appreciated!
AICU media’s new book ‘Image Generation AI Stable Diffusion Start Guide’ is now available for preorder! (Release date: March 29, 2024)
For more details, please visit https://ja.aicu.ai/sbxl/
The content of this article can also be viewed in AICU Magazine.
AICU Magazine Vol.1 April 2024 Issue https://j.aicu.ai/Mag2404
AICU Magazine Vol.1 May 2024 Issue https://j.aicu.ai/Mag2405
AICU: AI Creator Union is looking forward to your questions.
https://note.com/aicu/membership/boards
Originally published at https://note.com on March 19, 2024.
【Original Post】[Limited Time Free Edition］ Animagine XL 3.1 generation Comparison Resort (In Japanese)
https://note.com/aicu/n/n70122ef250d9
https://x.com/AICUai/status/1795354457737449494