How to run Playground v2.5 locally

Playground AI · Text → image · 3.5B params · Playground v2.5 Community License (commercial OK)

An SDXL-architecture model tuned for high aesthetic quality that beat SDXL and Midjourney 5.2 in the publisher's user studies.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 8.0 GB of VRAM (~8GB; SDXL-architecture, runs on consumer GPUs), via Diffusers / ComfyUI / Automatic1111.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at playgroundai/playground-v2.5-1024px-aesthetic.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → image
VRAM to run	~8.0 GB (~8GB; SDXL-architecture, runs on consumer GPUs)
Download	~7 GB
Parameters	3.5B
License	Playground v2.5 Community License (commercial use OK)
Run with	Diffusers / ComfyUI / Automatic1111

Get Playground v2.5 on Hugging Face →

More image models

FLUX.1 [dev] — Text → image, ~12 GB VRAM
Stable Diffusion XL 1.0 (SDXL) — Text → image, ~8.0 GB VRAM
Stable Diffusion 1.5 — Text → image, ~4.0 GB VRAM
FLUX.1 Kontext [dev] — Image editing, ~12 GB VRAM
FLUX.1 [schnell] — Text → image, ~12 GB VRAM
Qwen-Image — Text → image, ~24 GB VRAM

Browse: all media models · chat / LLM models