Check my GPU

Image models ·

PixArt-Σ XL 1024

Backbone
0.6B
Native output
1024×1024
Default steps
20
License
openrail++
Released
2024-04

How to run it

Original weights · Hugging Face

Full-precision files from PixArt, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from PixArt. The weights themselves download from Hugging Face.

github.com/PixArt-alpha/PixArt-sigma (opens in a new tab)

git clone https://github.com/PixArt-alpha/PixArt-sigma

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision Everything on GPU Text encoder offloaded Sequential offload Download
FP16 12.8 GB 3.3 GB 2.3 GB Original weights (opens in a new tab)

Components

Best hardware for PixArt-Σ XL 1024

The least expensive GPU in our catalog that runs it without offloading is the Intel Arc A380 (launch price $139) at FP16.

Grade · points Hardware Precision Memory Time per output Fit
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 AMD Radeon RX 9070 XT FP16 12.8 GB / 16.0 GB 2.0 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4060 Ti 16GB FP16 12.8 GB / 16.0 GB 4.0 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4070 Ti SUPER FP16 12.8 GB / 16.0 GB 2.4 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 4080 SUPER FP16 12.8 GB / 16.0 GB 2.1 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5060 Ti 16GB FP16 12.8 GB / 16.0 GB 3.8 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5070 Ti FP16 12.8 GB / 16.0 GB 2.4 s Runs well
77 ptsGreat (A) · 77 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA GeForce RTX 5080 FP16 12.8 GB / 16.0 GB 2.0 s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 12.3/15, Memory use 15.0/15 Apple M4 Pro (24 GB) FP16 12.8 GB / 16.1 GB 15 s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 AMD Radeon RX 7900 XTX FP16 12.8 GB / 24.0 GB 1.7 s Runs well
74 ptsGreat (A) · 74 of 100 points: Model quality 22.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 12.3/15 NVIDIA GeForce RTX 3090 FP16 12.8 GB / 24.0 GB 2.8 s Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.