Diffus
始める
モデル/Raemu XL - v3.5 Lightning

Raemu XL - v3.5 Lightning

Raelina
|
2/21/2026
|
8:53:30 PM
| Discussion|
0
Photorealistic woman with long black ponytail wearing a white futuristic bodysuit, standing indoors in a ruined building with cityscape in background.
Photorealistic depiction of a woman with black hair in a long ponytail, wearing a shiny blue futuristic bodysuit, kneeling indoors in a ruined building with tall structures visible through the broken walls.
金髪とピンクのグラデーションヘア、赤い目、黒いシャツ、チョーカーをつけたアニメ少女、室内。
金髪で赤い目のアニメ少女、黒いチョーカーと白い襟シャツを着た室内の画像。
長い金髪、ピンク色の目、複数のイヤーピアスをしたアニメの女の子が屋内で微笑んでいる。
室内で金髪、チョーカー、赤い瞳のアニメ少女が泣いている。

推奨プロンプト

masterpiece, high score, great score

masterpiece, best quality, very aesthetic, absurdres

(masterpiece, best quality, very aesthetic, ultra detailed), intricate details, 1girl

推奨ネガティブプロンプト

lowres, low score, bad score, worst quality, bad anatomy, bad hands, sketch, jpeg artifacts, text, error, signature, watermark

(low quality, worst quality:1.2), very displeasing, ugly, poorly drawn, signature, watermark

(worst quality, low quality, very displeasing, lowres), (interlocked fingers, badly drawn hands and fingers, anatomically incorrect hands), blurry, watermark

推奨パラメータ

samplers

Euler a

steps

8 - 35

cfg

2 - 7

resolution

1024x1024, 1152x896, 896x1152, 1216x832, 832x1216, 1344x768, 768x1344, 1536x640, 640x1536, 768x1344

推奨ハイレゾパラメータ

upscaler

4x-NMKD_YandereNeoXL, 4x_NMKD-YandereNeoXL_200k

upscale

2

steps

6 - 15

denoising strength

0.2

ヒント

Add 'quality' at the end of your prompts to improve image quality.

Refer to the Anim4gine Guidelines for best prompting practices: https://cagliostrolab.net/posts/optimizing-animagine-xl-40-in-depth-guideline-and-update

For faster generation with slightly lower quality, use the Lightning version settings with sampler Euler a, steps 8-10, CFG 2-2.5, upscaler 4x-NMKD_YandereNeoXL, hires steps 4-6, and denoising 0.1-0.3.

バージョンのハイライト

I tried my hand on the Lightning version.

I merged with Lightning LoRA and finetuning it after with 860 high-quality images.

What are the differences with v3 using Lightning LoRA:

  • More improved quality (I did finetuning on the Lightning checkpoint)

  • Reduced noise and artifacts

  • Reduced reddish coloring

Recommended Lightning Settings:

  • Sampler: Euler a

  • Sampling steps: 8-10

  • CFG: 2-2.5

  • Hires step: 4-6

  • Denoising: 0.1-0.3

Feel free to experiment, but I still recommend the settings above.

クリエイタースポンサー

Support the model development by purchasing early access or buying a coffee: Buy me a coffee on Ko-fi!

Learn more about Animagine 4.0 used as base: Animagine 4.0 Model

Use high-quality upscaler: 4x-NMKD_YandereNeoXL Upscaler

Raemu XL

Raemu XL is a SDXL-based anime model designed for 2.5D anime-style generation. It excels in producing high-quality, semi-realistic anime visuals with rich textures and refined shading.

V5

Raemu XL V5 is a finetuned iteration based on Animagine 4.0, further enhancing its ability to generate aesthetically refined 2.5D textures. This version improves lighting, depth, and overall visual quality while maintaining the signature anime look.

Ideal for high-quality illustrations, character art, and stylized anime rendering, Raemu XL delivers a balance between artistic expressiveness and fine detail.

Why Early Access?

Early access helps cover the cost of training and development. By purchasing early access, you're directly supporting the development of my models. If you'd like to support me further, you can also buy me a coffee on Ko-fi! Your support keeps the project going and ensures even better models in the future.

How to prompt.?

read Anim4gine GuideLines here

To guide the model towards generating high-aesthetic images, use negative prompts like:

lowres, low score, bad score, worst quality, bad anatomy, bad hands, sketch, jpeg artifacts, text, error, signature, watermark

For higher-quality results, add quality at the end of your prompts like:

masterpiece, high score, great score

  • Sampler : Euler a

  • Sampling steps : 28

  • CFG : 6

License

V5 model adopts the original CreativeML Open RAIL++-M License from Stability AI without any modifications or additional restrictions. The license terms remain exactly as specified in the original SDXL license, which includes:

  • ✅ Permitted: Commercial use, modifications, distributions, private use

  • ❌ Prohibited: Illegal activities, harmful content generation, discrimination, exploitation

  • ⚠️ Requirements: Include license copy, state changes, preserve notices

  • 📝 Warranty: Provided "AS IS" without warranties

Please refer to the original SDXL license for the complete and authoritative terms and conditions.

Below are for legacy V1-V4

SDXL anime base model that focused in 2.5D Anime. RaemuXL can generate high-quality anime images. This model merged from Animagine XL 3.0/3.1 as a base. Compatible with any Lora that trained from Animagine XL 3.0/3.1.

How to prompt.?

read Animagine GuideLines here

  • Sampler : Euler a

  • Sampling steps : 25-35

  • CFG : 7

The Lightning version has faster generation with a slightly decreased quality

  • Sampler : Euler a

  • Sampling steps : 8-10

  • CFG: 2-2.5

  • Upscaler : 4x-NMKD_YandereNeoXL

  • Hires step : 4-6

  • Denoising : 0.1-0.3

To guide the model towards generating high-aesthetic images, use negative prompts like:

(low quality, worst quality:1.2), very displeasing, ugly, poorly drawn, signature, watermark,

For higher quality outcomes, prepend prompts with:

masterpiece, best quality, very aesthetic, absurdres,

Multi Aspect Resolution

This model supports generating images at the following dimensions:

| Dimensions | Aspect Ratio |

|--------------|---------------|

| 1024 x 1024 | 1:1 Square |

| 1152 x 896 | 9:7 |

| 896 x 1152 | 7:9 |

| 1216 x 832 | 19:13 |

| 832 x 1216 | 13:19 |

| 1344 x 768 | 7:4 Horizontal |

| 768 x 1344 | 4:7 Vertical |

| 1536 x 640 | 12:5 Horizontal |

| 640 x 1536 | 5:12 Vertical |

License

Raemu XL now uses the Fair AI Public License 1.0-SD inherited from Animagine XL 3.0, compatible with Stable Diffusion models. Key points:

1. Modification Sharing: If you modify Raemu XL, you must share both your changes and the original license.

2. Source Code Accessibility: If your modified version is network-accessible, provide a way (like a download link) for others to get the source code. This applies to derived models too.

3. Distribution Terms: Any distribution must be under this license or another with similar rules.

4. Compliance: Non-compliance must be fixed within 30 days to avoid license termination, emphasizing transparency and adherence to open-source values.

For merge recipe go to my Huggingface Repo

前の画像
Minimalist Line Art (SDXL, Pony) - Flux
次の画像
Aurora - v1.0
このモデルを使用

モデル詳細

モデルタイプ

Checkpoint

ベースモデル

SDXL Lightning

モデルバージョン

v3.5 Lightning

モデルハッシュ

bbd321d4a3

作成者

Raelina's avatar
Raelina

ディスカッション

コメントを残すには log in してください。

「Raemu XL - v3.5 Lightning」による画像

Photorealistic woman with long black ponytail wearing a white futuristic bodysuit, standing indoors in a ruined building with cityscape in background.
Photorealistic depiction of a woman with black hair in a long ponytail, wearing a shiny blue futuristic bodysuit, kneeling indoors in a ruined building with tall structures visible through the broken walls.
金髪とピンクのグラデーションヘア、赤い目、黒いシャツ、チョーカーをつけたアニメ少女、室内。
金髪で赤い目のアニメ少女、黒いチョーカーと白い襟シャツを着た室内の画像。
長い金髪、ピンク色の目、複数のイヤーピアスをしたアニメの女の子が屋内で微笑んでいる。
室内で金髪、チョーカー、赤い瞳のアニメ少女が泣いている。

アニメ画像

Anime girl with long green hair crouching outdoors, petting a small black cat, surrounded by dense greenery and sunlight filtering through trees.
A thoughtful anime-style girl with light brown hair sits curled on a bench wearing a white basketball top and red patterned socks with blue sneakers.
A towering crystalline ice structure with sharp spikes set in a vast snowy landscape under a blue sky, with a solitary figure in dark clothing facing it.
A girl silhouette sits on a hill under a radiant Milky Way stretching vertically with aurora-like colors, set in a starry fantasy night anime style.
Anime-style nurse wearing a white uniform with red crosses, glasses, and long blonde hair, standing in a detailed hospital room with medical equipment.
Anime girl Yuri from Doki Doki Literature Club walking on a sunny street wearing a dark purple summer dress with floral pattern and a white brimmed hat.
Profile view of an anime girl in stylish urban streetwear wearing a black beanie with goggles, headphones, and carrying a transparent plastic bag on a wet city street.
A fierce young woman with black bob-cut hair and intense gaze wearing a white sailor-style top and pleated skirt, holding a detailed katana against a vivid red background.
A confident girl with burgundy hair in greyscale stands under a bridge at night wearing a black crop top, checkered jacket, and denim pants.

基本モデル画像

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

ファンタジー画像

A whimsical penguin riding a bicycle along a sandy beach at sunset, illustrated in a magical Ghibli style with soft painterly backgrounds and warm glowing light.
Detailed fantasy illustration of a boar-monster wearing a red brown police uniform with a peaked cap, leather gloves, and boots, holding a weapon.
A detailed fantasy troll sitting in a wooden barrel carriage with a greenish mossy dome, holding a staff and surrounded by small green fruits.
Cartoon axolotl characters dressed in black robes with tactical gear, one holding a pole with a black flag displaying a white axolotl design, standing over a kneeling jawa wearing an orange jumpsuit in a desert setting.
A white-haired girl with bright blue eyes stands smiling in a flowery meadow under a moonlit night sky, surrounded by flying petals and illuminated by cinematic lighting.
Glowing golden One Ring resting on a detailed Middle-earth map with cinematic dramatic lighting and shadows.
A girl riding on a giant orange goldfish surrounded by smaller goldfish and water bubbles in a bright blue sky
Hyper realistic oil painting of a punk rock girl with pink hair, wearing a Mad Max style black leather jacket and cables on her body, standing in an urban street setting.
A determined female knight with red hair in a high ponytail wearing black armor stands in a sunlit grassland holding a sword and shield with a fantasy castle in the background under a blue sky.

イラスト画像

Detailed Lego vikingpunk female figure wearing intricate futuristic golden and green armor with Celtic runes, a red cloak, and holding a red M41A rifle in a desert setting.
A woman with fiery, multicolored phoenix wings and flowing red hair curled in a fetal position, wearing a shiny gold dress, floating against a space backdrop.
Anime style drawing of a tired girl with dark circles sitting at a desk surrounded by piles of documents and a laptop in a warm-colored office environment, showing a confused and busy expression.
Black and white illustration of a black cat with a flowing tail in motion surrounded by abstract ink splatter and brush strokes on a minimalistic background.
A muscular male Yautja wearing armor sits against a tree on a grassy farm, surrounded by sheep under a blue sky with large white clouds.
A girl with dog ears wearing a green beret and cream cardigan holds a paper bag with baguettes, biting a sunflower-adorned bread slice under warm sunlight.
A Japanese dead noble Goryo spirit dressed in traditional kimono with katana, standing in front of a glowing haunted house under a full moon.
Portrait of a tattooed woman with long black hair and blue eyes, sitting against a red and white Japanese-style background, holding a katana and displaying intricate floral tattoos on her arms.
Anime-style nurse wearing a white uniform with red crosses, glasses, and long blonde hair, standing in a detailed hospital room with medical equipment.