Will It Run AI

Animagine XL 4.0

Stable

by Cagliostro Lab

Latest version of the popular anime-focused SDXL fine-tune from Cagliostro Lab. Successor to Animagine XL 3.1. Improved anime/illustration quality with better character consistency, more accurate tag-based prompting, and cleaner outputs.

VRAM requirements, GPU fit, and setup notes for Animagine XL 4.0, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~6.9 GB at FP16.

  • Best-in-class anime/illustration quality on SDXL
  • Improved character consistency over v3.1
  • Tag-based prompting (Danbooru tags)
  • Full SDXL LoRA ecosystem compatible
HuggingFaceDocumentation
242K downloads396 likes
ComfyUI, DiffusersFP16 safetensors

Your hardware

Detecting...

Parameters2.6B
Max Resolution1024×1024
Default Steps28
ArchitectureUNET
Licenseopenrail++

Image Quality Benchmarks

Measured quality metrics for Animagine XL 4.0 outputs.

Human Preference Score78%

How often humans prefer this model's output (0-100%)

Aesthetic Score7.5

Visual quality and composition rating (5-9 scale)

VRAM Requirements by Resolution and Precision

Compare which GPUs can run Animagine XL 4.0 at different precisions. FP8 uses less memory than FP16 when available, and the grade shows how comfortably each GPU handles the workload.

FP16 (full precision)

ResolutionVRAM RequiredRTX 4090 24GBRTX 3060 12GBRTX 4060 8GBMacBook Pro M4 Pro 24GB
512×5127.6 GBSSBS
768×7687.8 GBSSBS
1024×10248.0 GBSSBS

Optimization Tips

Turbo / LCM distillation

Use distilled scheduler at 4-8 steps for faster iteration

ControlNets available

Add guided generation with 3 adapters (+1.2 GB VRAM each)

Rich LoRA ecosystem

Customize style, characters, and quality with community LoRAs

Run with Python

Run with Python (diffusers)
from diffusers import StableDiffusionXLPipeline
import torch

pipe = StableDiffusionXLPipeline.from_pretrained(
    "cagliostrolab/animagine-xl-4.0",
    torch_dtype=torch.float16
)
pipe.to("cuda")

image = pipe(
    prompt="your prompt here",
    num_inference_steps=28,
    guidance_scale=7.5,
    height=1024,
    width=1024,
).images[0]
image.save("output.png")

Get started

Setup instructions for running Animagine XL 4.0 locally

1. Download the model

Get the checkpoint from HuggingFace

2. Place in:

ComfyUI/models/checkpoints/

3. Launch ComfyUI

python main.py
Tip: For SDXL fine-tunes, you can optionally add the SDXL refiner for improved detail. Place the refiner checkpoint in the same folder and add a second KSampler with denoise ~0.3.

Memory Breakdown

VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)

Required: 8.0 GBAvailable: 24.0 GB
Weights5.2 GB
VAE0.2 GB
Text Encoder1.6 GB
Activations0.5 GB
Overhead0.5 GB

Estimated Generation Time

Time per image at 1024×1024, 28 steps, FP16.

RTX 4090 24GB~4.5s
RTX 3060 12GB~17s
RTX 4060 8GB~1m 8s
MacBook Pro M4 Pro 24GB~36.4s

Sample Outputs

Available Formats, Downloads & Setup

Download Animagine XL 4.0 in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.

FormatoPrecisãoTamanhoProvedor
safetensorsRecomendadoFP166.9 GBofficialBaixar

ControlNet Support

3 ControlNets available for Animagine XL 4.0. ControlNets add guided image generation (edges, depth, pose) at the cost of extra VRAM.

Canny Edge

+1.2 GB VRAM

Edge detection for structural guidance. Full SDXL ControlNet compatibility.

comfyuiautomatic1111diffusers
View on HF

Depth Map

+1.2 GB VRAM

Depth-based spatial control for maintaining 3D composition.

comfyuiautomatic1111diffusers
View on HF

OpenPose

+1.2 GB VRAM

Human pose control for character positioning and body language.

comfyuiautomatic1111diffusers
View on HF

LoRA Ecosystem

Large Ecosystem

Full SDXL LoRA ecosystem plus anime-specific LoRAs on CivitAI. Extensive character and style LoRAs.

Browse all LoRAs on CivitAI
Fine-tune of sdxl-1-0

Related Workflows

You might also like

Frequently asked questions

FAQ — Animagine XL 4.0 VRAM, Runtimes & Fit

How much VRAM does Animagine XL 4.0 need?

Animagine XL 4.0 (2.6B parameters) requires approximately 8.0 GB of VRAM at FP16 precision for standard 1024×1024 image generation. If you want a lighter setup, lower precisions like FP8 can reduce memory use when available.

Can I run Animagine XL 4.0 on an 8GB GPU?

Animagine XL 4.0 usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.

Does Animagine XL 4.0 work in ComfyUI and Diffusers?

Animagine XL 4.0 is marked for ComfyUI and Diffusers support in our catalog, so those are the runtimes we recommend first for local setup. If your workflow uses another front end, check the model's available formats and workflow notes above before downloading.

Can I run Animagine XL 4.0 on RTX 4090?

Yes, the RTX 4090 (24 GB VRAM) can run Animagine XL 4.0 comfortably at FP16. Expected generation time is around ~4.5s per image at 1024×1024.

Does Animagine XL 4.0 support ControlNet?

Yes, Animagine XL 4.0 has 3 ControlNet adapters available: Canny Edge, Depth Map, OpenPose. Each ControlNet adds roughly 1.2 GB of extra VRAM.

Does Animagine XL 4.0 have LoRA support?

Full SDXL LoRA ecosystem plus anime-specific LoRAs on CivitAI. Extensive character and style LoRAs. The LoRA ecosystem for Animagine XL 4.0 is rated as "large". Each LoRA adds roughly 0.2 GB of extra VRAM.

How fast is Animagine XL 4.0?

On a reference GPU (RTX 4090 24GB), Animagine XL 4.0 generates a 1024×1024 image in approximately ~4.5s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.

About Animagine XL 4.0

Use cases
animeillustrationcharacter-design
Recommended runtimes
comfyuidiffusers

See also