CompVis / text-to-image updated 2 years ago

stable-diffusion-v1-4

Name: stable-diffusion-v1-4
Author: CompVis

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at 🤗's Stable Diffusion with 🧨Diffusers blog.

Params

860 M

Context

—

Downloads 30d

447 K

Likes

7,048

Commercial use: conditional · creativeml-openrail-m Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

447 K425 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f32	11.7 GB	13.5 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters: 860 M
Tensor type: F32
Licence: creativeml-openrail-m
First seen on the Hub: 2022-08-20
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

stable-diffusion-v1-5 1.6 M stable-diffusion-xl-base-1.0 1.5 M dreamshaper-7 895 K Flux2-Klein-9B-True-V2 792 K sd-turbo 722 K Realistic_Vision_V5.1_noVAE 485 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB