wikeeyang / text-to-image updated 6 months ago

Real-Qwen-Image-V2

Name: Real-Qwen-Image-V2
Author: wikeeyang

本模型为 Qwen-Image-2512 的微调模型，比官方模型具有更好的锐度和真实感，以及对亚洲人脸美学进行了优化。具体效果参见如下示例图片，本模型易于使用、参数适配性和LoRA兼容性良好，文字和出图品质俱佳，真正的开源生产力工具。

Params

—

Context

—

Downloads 30d

31 K

Likes

Commercial use: allowed apache-2.0 Not gated GGUF · SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

31 K31 K

Jul 28Jul 31Aug 3Aug 6

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
Real-Qwen-Image-V2-2512-Q4_K_M.gguf	Q4_K_M	13.1 GB	14.9 GB	✅ Runs comfortably
Real-Qwen-Image-V2-2512-Q8_0.gguf	Q8_0	21.8 GB	24.4 GB	❌ Won’t fit
model.safetensors	fp16	33.8 GB	37.7 GB	❌ Won’t fit

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

Base model and the most-downloaded derivatives in the catalog.

Compare with

Appears in

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