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.
Your hardware
Detecting...
Measured quality metrics for PixArt-Sigma outputs.
How often humans prefer this model's output (0-100%)
Visual quality and composition rating (5-9 scale)
Text-image alignment accuracy (higher is better)
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.
| Resolution | VRAM Required | RTX 4090 24GB | RTX 3060 12GB | RTX 4060 8GB | MacBook Pro M4 Pro 24GB |
|---|---|---|---|---|---|
| 512×512 | 5.8 GB | S● | S● | S● | S● |
| 768×768 | 5.9 GB | S● | S● | S● | S● |
| 1024×1024 | 6.0 GB | S● | S● | S● | S● |
Turbo / LCM distillation
Use distilled scheduler at 4-8 steps for faster iteration
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.pyComfyUI Workflow
Basic txt2img workflow for PixArt-Sigma
Drag & drop into ComfyUI or use File → Import
VRAM allocation at 1024×1024 on RTX 4090 24GB (24 GB)
Time per image at 1024×1024, 28 steps, FP16.
Download PixArt-Sigma in the precision that matches your GPU. Lower precision usually means less VRAM pressure, while higher precision keeps more quality.
| Format | Precision | Size | Provider | |
|---|---|---|---|---|
| safetensorsRecommended | FP16 | 1.2 GB | official | Download |
Frequently asked questions
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.
PixArt-Sigma usually needs more than 8GB for comfortable local use. Check the VRAM table above for the exact resolution and precision trade-off.
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.
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.
There are currently no known ControlNet adapters for PixArt-Sigma. Check Hugging Face and Civitai for community-contributed adapters.
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.
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.
See also