CyberRealisticXL
CyberRealistic XL is a photorealistic image generation model based on Stable Diffusion XL 1.0 (SDXL). It is designed to produce highly realistic, cinematic-quality outputs with minimal prompt engineering. This checkpoint is optimized for portraits, fashion, and editorial-style scenes, but also handles a wide range of creative prompts with remarkable fidelity.
Params
—
Context
—
Downloads 30d
35 K
Likes
42
Download history
daily snapshots · 38 days
▲ 12 K in the last 30 days (54.4%)
36 K23 K
Aug 22Sep 1Sep 11Sep 20
36 K16 K
Aug 14Aug 26Sep 8Sep 20
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 | fp16 | 208.1 GB | 229.5 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
- Licence
- creativeml-openrail-m
- First seen on the Hub
- 2024-02-21
- Training datasets
- undisclosed
- Added to our catalog
- 2026-08-14
Compare with any text-to-image model