CIDAS / image-segmentation updated 1 year ago

clipseg-rd64-refined

Name: clipseg-rd64-refined
Author: CIDAS

CLIPSeg model with reduce dimension 64, refined (using a more complex convolution). It was introduced in the paper Image Segmentation Using Text and Image Prompts by Lüddecke et al. and first released in this repository.

Params

150 M

Context

—

Downloads 30d

1.1 M

Likes

141

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.1 M1.1 M

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	0.6 GB	1.2 GB	✅ Runs comfortably

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

Specifications

Architecture: CLIPSegForImageSegmentation
Parameters: 150 M
Tensor type: F32
Licence: apache-2.0
First seen on the Hub: 2022-11-01
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

BiRefNet 715 K RMBG-2.0 702 K mask2former-swin-large-ade-semantic 625 K segformer-b0-finetuned-ade-512-512 364 K segformer-b2-finetuned-ade-512-512 338 K RMBG-1.4 319 K

Appears in

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