wikeeyang / text-to-image updated 3 weeks ago

Krea2-Turbo-HD-V1

Name: Krea2-Turbo-HD-V1
Author: wikeeyang

Krea2-Turbo HD optimized version, with synchronized fine-tuned VAE, more details, better texture.

Params

—

Context

—

Downloads 30d

43 K

Likes

Licence: other Not gated GGUF · SAFETENSORS 2 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

43 K39 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
Krea2-Turbo-HD-V1-NVFP4.gguf	GGUF	8.2 GB	9.5 GB	✅ Runs comfortably
Krea2-Turbo-HD-V1-Q4_K_S.gguf	Q4_K_S	8.2 GB	9.5 GB	✅ Runs comfortably
Krea2-Turbo-HD-V1-Q5_K_S.gguf	Q5_K_S	9.5 GB	11.0 GB	✅ Runs comfortably
Krea2-Turbo-HD-V1-Q6_K.gguf	Q6_K	10.9 GB	12.5 GB	✅ Runs comfortably
Krea2-Turbo-HD-V1-Q8_0.gguf	Q8_0	13.9 GB	15.8 GB	✅ Runs comfortably
model.safetensors	fp16	59.2 GB	65.7 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