gsdf / text-to-image Open weights updated 3 years ago

Counterfeit-V2.5

V2.5 has been updated for ease of use as anime-style model. I use this embedding for negative prompts. https://huggingface.co/datasets/gsdf/EasyNegative

Params
860 M
Context
—
Downloads 30d
92 K
Likes
1,596
Commercial use: conditional · creativeml-openrail-m Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 16 days
92 K39 K
Oct 26Oct 31Nov 5Nov 10

Can you run it?

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

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
model.safetensors f32 26.9 GB 30.2 GB ❌ Won’t fit
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
2023-02-02
Training datasets
undisclosed
Added to our catalog
2026-10-26
Compare with any text-to-image model