Will It Run AI
pixart

PixArt-Sigma

Stable

by PixArt

Ultra-lightweight DiT model with only 0.6B parameters. Generates 1024px images with surprisingly good quality for its size. Uses T5-XXL text encoder for strong prompt adherence despite small UNet.

VRAM requirements, GPU fit, and setup notes for PixArt-Sigma, including 8GB/12GB fit guidance where relevant. Recommended runtimes: ComfyUI and Diffusers support. Best download size: ~1.2 GB at FP16.

  • Only 0.6B UNet params — ultra lightweight
  • Supports up to 1024px despite tiny size
  • Uses T5-XXL for strong prompt adherence
  • Great quality-to-size ratio
ComfyUI, DiffusersFP16 safetensors

Your hardware

Detecting...

Parameters0.611B
Max Resolution1024×1024
Default Steps20
ArchitectureDIT
Licenseopenrail++

Image Quality Benchmarks

Measured quality metrics for PixArt-Sigma outputs.

Human Preference Score68%

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

Aesthetic Score6.8

Visual quality and composition rating (5-9 scale)

CLIP Score0.28

Text-image alignment accuracy (higher is better)

VRAM Requirements by Resolution and Precision

Compare which GPUs can run PixArt-Sigma 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
512×5125.8 GBSSSS
768×7685.9 GBSSSS
1024×10246.0 GBSSSS

Optimization Tips

Turbo / LCM distillation

Use distilled scheduler at 4-8 steps for faster iteration

Run with Python

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

pipe = PixArtSigmaPipeline.from_pretrained(
    "PixArt-alpha/PixArt-Sigma-XL-2-1024-MS",
    torch_dtype=torch.float16
)
pipe.to("cuda")

image = pipe(
    prompt="your prompt here",
    num_inference_steps=20,
    guidance_scale=4.5,
    height=1024,
    width=1024,
).images[0]
image.save("output.png")

Get started

Setup instructions for running PixArt-Sigma locally

1. Download the model

Get the checkpoint from HuggingFace

2. Place in:

ComfyUI/models/checkpoints/

3. Launch ComfyUI

python main.py

ComfyUI Workflow

Basic txt2img workflow for PixArt-Sigma

8 nodes

Drag & drop into ComfyUI or use File → Import

Memory Breakdown

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

Required: 6.0 GBAvailable: 24.0 GB
Weights1.2 GB
VAE0.2 GB
Text Encoder9.4 GB
Activations0.6 GB
Overhead0.5 GB

Estimated Generation Time

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

RTX 4090 24GB~4s
RTX 3060 12GB~1m 8s
RTX 4060 8GB~22.8s
MacBook Pro M4 Pro 24GB~32.4s

Sample Outputs

Available Formats, Downloads & Setup

Download PixArt-Sigma in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.

格式精度大小提供商
safetensors推荐FP161.2 GBofficial下载

Related Workflows

You might also like

Frequently asked questions

FAQ — PixArt-Sigma VRAM, Runtimes & Fit

How much VRAM does PixArt-Sigma need?

PixArt-Sigma (0.611B parameters) requires approximately 6.0 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 PixArt-Sigma on an 8GB GPU?

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

Does PixArt-Sigma work in ComfyUI and Diffusers?

PixArt-Sigma 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 PixArt-Sigma on RTX 4090?

Yes, the RTX 4090 (24 GB VRAM) can run PixArt-Sigma comfortably at FP16. Expected generation time is around ~4s per image at 1024×1024.

Does PixArt-Sigma support ControlNet?

There are currently no known ControlNet adapters for PixArt-Sigma. Check Hugging Face and Civitai for community-contributed adapters.

Does PixArt-Sigma have LoRA support?

No LoRA ecosystem for PixArt-Sigma. The LoRA ecosystem for PixArt-Sigma is rated as "none". Each LoRA adds roughly 0.0 GB of extra VRAM.

How fast is PixArt-Sigma?

On a reference GPU (RTX 4090 24GB), PixArt-Sigma generates a 1024×1024 image in approximately ~4s at FP16 with 28 inference steps. Faster GPUs with higher memory bandwidth will produce images more quickly.

About PixArt-Sigma

Use cases
artdesignfast-generation
Recommended runtimes
comfyuidiffusers

See also