Animagine XL 3.1
Stableby Cagliostro Lab
Top anime SDXL fine-tune using Danbooru tag-based prompting. Excellent character generation with consistent anatomy and style. One of the most downloaded anime models on HuggingFace.
VRAM requirements, GPU fit, and setup notes for Animagine XL 3.1, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI, Automatic1111, and Diffusers support. Best download size: ~6.9 GB at FP16.
- Top anime model on SDXL
- Danbooru tag-based prompting
- Excellent character generation
Your hardware
Detecting...
Image Quality Benchmarks
Measured quality metrics for Animagine XL 3.1 outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
VRAM Requirements by Resolution and Precision
Compare which GPUs can run Animagine XL 3.1 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)
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 7.6 GB | S● | S● | B● | S● |
| 768×768 | 7.8 GB | S● | S● | B● | S● |
| 1024×1024 | 8.0 GB | S● | S● | B● | S● |
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
from diffusers import StableDiffusionXLPipeline
import torch
pipe = StableDiffusionXLPipeline.from_pretrained(
"cagliostrolab/animagine-xl-3.1",
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 3.1 locally
1. Download the model
Get the checkpoint from HuggingFace
2. Place in:
ComfyUI/models/checkpoints/3. Launch ComfyUI
python main.pyComfyUI Workflow
Basic txt2img workflow for Animagine XL 3.1
Drag & drop into ComfyUI or use File → Import
Memory Breakdown
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Estimated Generation Time
Time per image at 1024×1024, 28 steps, FP16.
Sample Outputs
Available Formats, Downloads & Setup
Download Animagine XL 3.1 in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
| Formato | Precisão | Tamanho | Provedor | |
|---|---|---|---|---|
| safetensorsRecomendado | FP16 | 6.9 GB | Cagliostro Lab | Baixar |
ControlNet Support
3 ControlNets available for Animagine XL 3.1. ControlNets add guided image generation (edges, depth, pose) at the cost of extra VRAM.
Canny Edge (SDXL)
+1.2 GB VRAMInherits SDXL base model ControlNet compatibility. Edge-based structural guidance.
Depth Map (SDXL)
+1.2 GB VRAMInherits SDXL base model ControlNet compatibility. Depth-based spatial control.
OpenPose (SDXL)
+1.2 GB VRAMInherits SDXL base model ControlNet compatibility. Human pose control.
LoRA Ecosystem
Large EcosystemInherits full SDXL LoRA ecosystem. Many anime-specific LoRAs trained directly on Animagine.
Browse all LoRAs on CivitAIRelated Workflows
You might also like
Frequently asked questions
FAQ — Animagine XL 3.1 VRAM, Runtimes & Fit
How much VRAM does Animagine XL 3.1 need?
Animagine XL 3.1 (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 3.1 on an 8GB GPU?
Animagine XL 3.1 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 3.1 work in ComfyUI and Automatic1111?
Animagine XL 3.1 is marked for ComfyUI, Automatic1111, 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 3.1 on RTX 4090?
Yes, the RTX 4090 (24 GB VRAM) can run Animagine XL 3.1 comfortably at FP16. Expected generation time is around ~4.5s per image at 1024×1024.
Does Animagine XL 3.1 support ControlNet?
Yes, Animagine XL 3.1 has 3 ControlNet adapters available: Canny Edge (SDXL), Depth Map (SDXL), OpenPose (SDXL). Each ControlNet adds roughly 1.2 GB of extra VRAM.
Does Animagine XL 3.1 have LoRA support?
Inherits full SDXL LoRA ecosystem. Many anime-specific LoRAs trained directly on Animagine. The LoRA ecosystem for Animagine XL 3.1 is rated as "large". Each LoRA adds roughly 0.2 GB of extra VRAM.
How fast is Animagine XL 3.1?
On a reference GPU (RTX 4090 24GB), Animagine XL 3.1 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 3.1
See also