clipseg-rd64-refined vs face-parsing
Specs, VRAM requirements and download trends — updated 24 October 2026.
CIDAS · A · Open weights
Params
150 M
Context
—
30d
580 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | clipseg-rd64-refined | face-parsing |
|---|---|---|
| Parameters | 150 M | 85 M |
| Architecture | CLIPSegForImageSegmentation | SegformerForSemanticSegmentation |
| Context length | — | — |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 580,178 | 183,467 |
| Downloads all time | 152.9 M | 10.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-11-01 | 2022-07-06 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.3 M183 K
clipseg-rd64-refined
face-parsing
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
face-parsing · fp16
0.9 GB / 24 GB
clipseg-rd64-refined · fp16
1.2 GB / 24 GB
Adjacent comparisons
clipseg-rd64-refined vs BiRefNet
clipseg-rd64-refined vs mask2former-swin-large-ade-semantic
clipseg-rd64-refined vs segformer-b0-finetuned-ade-512-512
clipseg-rd64-refined vs mask2former-swin-large-cityscapes-semantic
clipseg-rd64-refined vs RMBG-2.0
clipseg-rd64-refined vs segformer-b2-finetuned-ade-512-512