second-state / text-to-image updated 1 year ago

stable-diffusion-v1-5-GGUF

bash wasmedge --dir .:. sd-api-server.wasm \ --model-name sd-v1.5 \ --model stable-diffusion-v1-5-pruned-emaonly-Q80.gguf

Params
Context
Downloads 30d
22 K
Likes
32
Commercial use: conditional · creativeml-openrail-m Not gated GGUF · SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 10 days
23 K22 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.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
stable-diffusion-v1-5-pruned-emaonly-Q4_0.gguf Q4_0 1.6 GB 2.2 GB ✅ Runs comfortably
stable-diffusion-v1-5-pruned-emaonly-Q4_1.gguf Q4_1 1.6 GB 2.3 GB ✅ Runs comfortably
stable-diffusion-v1-5-pruned-emaonly-Q5_0.gguf Q5_0 1.6 GB 2.3 GB ✅ Runs comfortably
stable-diffusion-v1-5-pruned-emaonly-Q5_1.gguf Q5_1 1.6 GB 2.3 GB ✅ Runs comfortably
stable-diffusion-v1-5-pruned-emaonly-Q8_0.gguf Q8_0 1.8 GB 2.4 GB ✅ Runs comfortably
stable-diffusion-v1-5-pruned-emaonly-f32.gguf GGUF 4.3 GB 5.2 GB ✅ Runs comfortably
model.safetensors fp16 4.3 GB 5.2 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
creativeml-openrail-m
First seen on the Hub
2024-07-09
Training datasets
undisclosed
Added to our catalog
2026-07-28