SDXL

Illustrious-XL-v2.0

Illustrious-XL-v2.0 - AI Model cover image
Trainiert von
Avatar image of Onoma AI

Onoma AI

Hochgeladen am
13.03.2025, 16:42
Verwendet
421k
Bewertungen
Gut  (40)
Sampling-Schritte

28

Sampling-Methode

Euler a

CFG scale

7.5

Negativ

worst quality, bad quality, very displeasing, displeasing, bad anatomy, artistic error, lowres, bad hands, signature, artist name, multiple views, variations, old, oldest, missing fingers, excess fingers, extra hands

Berechtigungen
  • Bildgenerierung und -freigabe erlauben
  • Nutzern erlauben, dieses Modell herunterzuladen
  • Gewerbliche Nutzung

Empfohlene LoRAs

Beschreibung

We’re excited to share that you can now generate images directly with our Illustrious XL models on our official site: [illustrious-xl.ai](http://illustrious-xl.ai/).

We’ve launched a full image generation platform featuring high-res outputs, natural language prompting, and custom presets - plus, several exclusive models you won’t find on any other hub.

Explore our updated model tiers and naming here: [Model Series](https://www.illustrious-xl.ai/updates/20).

Need help getting started? Check out our generation user guide: [ILXL Image Generation User Guide](https://www.illustrious-xl.ai/updates/21).

Illustrious XL 2.0: Increased robustness for better fine-tuning capabilities From now on, all updates will be also posted directly on our site!

For the v2.0 model’s technical details, check out: https://www.illustrious-xl.ai/blog

Stay in the loop with our latest releases and updates at: https://www.illustrious-xl.ai

In this version, the dataset has increased drastically, including major focus on animations & natural language focus with updated dataset, until 2024-08.

The model has performed best finetuning stability in our internal tests with highest TrueSkill rating(among v1-v2) in external demo evaluation.

Illustrious XL 2.0: Increased robustness for better fine-tuning capabilities

In this version, the dataset has increased drastically, including major focus on animations & natural language focus – with updated dataset, until 2024-08.

The model has performed best finetuning stability in our internal tests with highest TrueSkill rating(among v1-v2) in external demo evaluation.

We want to note that we consider the compatibility & finetuning capability the most important feature of our baseline model.

The model itself is not trained with aesthetic set / and we tried our best to debias the potential biases in model, for better overall performance.

Thus, we release ‘untuned’ base version, which should work as better merging / training bases. With release of the models, we also showcase example LoRA adapters, which is widely compatible across versions with recent character knowledges.

Natural Language Handling The model itself is highly compatible with natural language sentences it is far more robust, it is less likely to generate multiple views or nonsense outputs.

Kommentare

Kunstwerk gemacht von Illustrious-XL-v2.0

1
AI artwork featuring #Onikata Kayoko generated with Illustrious-XL-v2.0
Avatar image of kyo
avatar-frame
artist:z3zz4, artist:ask \(askzy\), artist:modare, artist:wanke, artist:rustle, kayoko \(blue archive\), kayoko \(dress\) \(blue archive\), 1girl, black bow, black choker, black footwear, black horns, bow, breasts, choker, cleavage, closed mouth, collarbone, demon horns, demon wings, dutch angle, ear piercing, full body, gradient hair, grey halo, hair between eyes, hair bow, halo, hand on own hip, horns, long hair, looking to the side, mole, mole on collarbone, multicolored hair, nail polish, official alternate costume, piercing, red eyes, simple background, single sidelock, single wing, sleeves past wrists, small breasts, solo, standing, strap slip, studded choker, two-tone hair, white background, wings, 8nmeter, blue archive , masterpiece, best quality, amazing quality, very aesthetic, absurdres, best quality, newest,
kyo
AI artwork generated with Illustrious-XL-v2.0
ss
an illustration of a person leaning against a wall, male focus, 1boy, jewelry, looking at viewer, black hair, necklace, snow, short hair, dark grey eyes, looking at viewer, detailed background, beautiful art,male focus,handsome anime boy, defined facial features, volumetric shading,1male, sketch,Beautiful eyes, art style, pretty face, black eyeliner, solo,sketch style, soft brush touches, soft lining, detailed hair depiction, high quality, masterpiece, best quality, Emphasize a blend of anime aesthetics with painterly digital rendering techniques, rich colors, emotive expression,Dramatic Lighting, The use of light and shadow creates a moody atmosphere,
sc sc
1
AI artwork generated with Illustrious-XL-v2.0
Avatar image of kyo
avatar-frame
[artist:ningenmame],[artist:ciloranko],[artist:shosho_lwlw],[[artist:tianliang_duohe_fangdongye, artist:as109]],hatsune miku, 1girl, black jacket, blue hair, cellphone, collared shirt, colored eyelashes, cracked phone, eyepatch, fisheye, heart, holding, holding phone, jacket, leaning forward, long hair, long sleeves, medical eyepatch, miniskirt, necktie, open mouth, phone, pleated skirt, shirt, skirt, smartphone, smile, solo, standing, twintails, white shirt, hassan \(sink916\), monitoring \(vocaloid\), vocaloid
kyo