Diffus
Get started
models/Raemu XL - v3.5 Lightning

Raemu XL - v3.5 Lightning

Raelina
|
11/13/2025
|
12:03:27 PM
| Discussion
Photorealistic image of a woman with a long ponytail wearing a sleek white futuristic bodysuit, standing indoors in a ruined building with urban decay and sunlight streaming through broken arches.
Realistic image of a woman with a long ponytail wearing a blue futuristic bodysuit kneeling in a ruined indoor city environment under soft daylight, showing detailed textures and reflective surfaces.
An AI generated image using stable diffusion of an anime girl with long blonde hair and pink highlights, wearing a black choker and black shirt, with red eyes and a slightly sad expression, standing in a modern room.
Anime girl with long blonde hair, red eyes, pink highlights, and a black choker necklace, generated by AI using stable diffusion.
Anime girl with long blonde hair, pink eyes, and ear piercings, wearing a black top, created using AI with Stable Diffusion.
AI generated image of an anime girl with long blond hair, red eyes, and a choker, crying with tears streaming down her face. Created using Stable Diffusion.

Recommended Prompts

masterpiece, high score, great score

masterpiece, best quality, very aesthetic, absurdres

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

Recommended Negative Prompts

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

Recommended Parameters

samplers

Euler a

steps

8 - 35

cfg

2 - 7

resolution

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

Recommended Hires (High-Resolution) Parameters

upscaler

4x-NMKD_YandereNeoXL, 4x_NMKD-YandereNeoXL_200k

upscale

2

steps

6 - 15

denoising strength

0.2

Tips

Use negative prompts to avoid low quality: lowres, bad anatomy, bad hands, sketch, jpeg artifacts, text, error, signature, watermark.

Add quality descriptors at the end of prompts like masterpiece, high score, great score for enhanced output quality.

Refer to Anim4gine Guidelines for optimized prompting and usage.

The model supports multi-aspect ratio resolutions like 1024x1024, 1152x896, 896x1152, etc.

The Lightning version offers faster generation with lower quality (Sampler: Euler a, steps: 8-10, CFG: 2-2.5).

Version Highlights

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.

Creator Sponsors

Early access helps cover training costs. Support the developer by purchasing early access or buying a coffee on Ko-fi. Your support ensures continued development and better future models.

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

Previous
Style | Odyk - v1.0
Next
Eve - Stellar Blade - Flux1.D SDXL - v1.0 SDXL
Use this model

Model Details

Model type

Checkpoint

Base model

SDXL Lightning

Model version

v3.5 Lightning

Model hash

bbd321d4a3

Creator

Raelina's avatar
Raelina

Discussion

Please log in to leave a comment.

Images by Raemu XL - v3.5 Lightning

Photorealistic image of a woman with a long ponytail wearing a sleek white futuristic bodysuit, standing indoors in a ruined building with urban decay and sunlight streaming through broken arches.
Realistic image of a woman with a long ponytail wearing a blue futuristic bodysuit kneeling in a ruined indoor city environment under soft daylight, showing detailed textures and reflective surfaces.
An AI generated image using stable diffusion of an anime girl with long blonde hair and pink highlights, wearing a black choker and black shirt, with red eyes and a slightly sad expression, standing in a modern room.
Anime girl with long blonde hair, red eyes, pink highlights, and a black choker necklace, generated by AI using stable diffusion.
Anime girl with long blonde hair, pink eyes, and ear piercings, wearing a black top, created using AI with Stable Diffusion.
AI generated image of an anime girl with long blond hair, red eyes, and a choker, crying with tears streaming down her face. Created using Stable Diffusion.

anime Images

Cybernetic female android wearing a black and white skull mask with camouflage armor, holding two futuristic guns in a dynamic pose under a structure in a rocky environment.
A slender Japanese woman with porcelain skin and raven-black hair wearing a sleek avant-garde black outfit stands confidently against a wintry, holographic sky with soft pastel hues, evoking a dreamy winter morning.
A glowing white-winged angelic figure stands amidst cracked ruins holding a luminous horizontal sword, surrounded by a dark, mysterious, cinematic environment.
Anime-style female character with dark hair, wearing kaleidoscopic sunglasses and licking a pink and white lollipop, her transparent face blending into a vivid liquid dreamscape of colors and lights.
Mysterious cyberpunk cultist nun with a golden chained veil, wearing a futuristic black and white overcoat in a dense jungle illuminated by red neon light.
Anime-style illustration of VTuber Kson with blue hair tied in a ponytail adorned with a blue flower, wearing sunglasses on her head, a choker, and striped dress, drinking bubble tea through a pink straw against a clear blue sky.
A young girl sitting in front of a tall blue building under a clear sky, wearing a white baseball cap, white jacket with hood, black pants, and white sneakers, with backpacks around her.
A chibi-style character with long blonde hair is jumping midair against a blue background, smiling happily with arms spread and a red string of fate floating around.
Scenic Scandinavian lake surrounded by dense forest under a vibrant orange sunset sky, with clouds reflected in the water and mountains in the background.
Overhead view of soft, rolling sand dunes in a vast Scandinavian desert under a warm orange sunset sky with birds soaring above, illustrated in anime style.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

fantasy Images

Closeup view of a cyberpunk-inspired abstract scene with dramatic lighting, featuring red squares raining down over dark green futuristic structures.
Silhouette of a bunny-eared girl standing on a swing attached to a large treehouse surrounded by blue foliage with water reflecting the scene below.
A vibrant and whimsical scene featuring a joyful girl with long multicolored hair and a colorful dress, dancing with arms raised among giraffes, balloons, and confetti beneath a bright blue sky and a large rainbow.
A biomorphic aquatic creature with translucent fins and a long stinging tail swims in a dramatic underwater environment surrounded by colorful coral reefs and fish.
A semi-realistic fantasy android cyborg with glowing orange eyes, covered in green leaves and branches, featuring a large white flower on its head against a black background.
A romantic couple sits at a wooden table under soft afternoon light streaming through weathered French double windows, overlooking a turquoise lake and green mountains.
A terrified couple hugging on a red couch while surrounded by menacing demonic creatures with glowing eyes and fangs, illustrated in a detailed fantasy style.
Fantasy scene of two elves resting under a large sacred tree at sunset with glowing lanterns, vibrant flowers, and a starry sky filled with magical stars.
A towering hooded dark figure stands in a desolate post-apocalyptic landscape beneath a bleeding red orb, surrounded by crumbling buildings and dark stormy skies.
Hyper-realistic fantasy portrait of a young woman with glowing orange eyes, wearing an intricate metallic mask and a flowing blue scarf with abstract patterns.

illustration Images

A giant monstrous yellow 3D Pacman with sharp teeth and a wide open mouth emits a cascading eerie stream over planet Earth, symbolizing planet destruction in a dark fantasy art style.
Stylized silhouette of a girl with a belt pouch and braided hair in partial color on a light background
Illustration of a gelatinous cube glowing with a reality-bending aura on the roof of a small abandoned building on a rocky hill, surrounded by trees, in a post-apocalyptic mythical mountain setting during midnight with vintage colors and warm volumetric lighting.
A comic book style illustration of a stone spiral staircase inside a dark underground cave, with a mysterious figure in a cloak standing at the bottom.
Portrait of a curvaceous alien with a machine-like face featuring intricate robotic details and armor in a highly detailed digital painting style inspired by Horizon Zero Dawn and artists Artgerm, Greg Rutkowski, and Alphonse Mucha.
A female warrior with silver hair in traditional armor holding a katana in an action pose, set against a vivid red background with cherry blossoms.
Watercolor style illustration of a bison in soft pastel colors, emerging from mist and snow with a foggy, atmospheric background
Two girls seated on a roller coaster at an amusement park; one is teary-eyed and excited, the other smiles confidently, both wearing blue outfits with white collars under bright daylight and a ferris wheel in the background.
A serene girl with lavender hair sitting barefoot in a moonlit field adorned with glowing butterflies and wearing an elegant floral fantasy dress.
Jelly Hoshiumi with blue gradient hair and yellow star antennae swings joyfully on a pastel yellow swing suspended in a dreamy sky playground with glowing clouds and soft stars.