A/B Blind Taste Test - Krea2-Turbo vs. Qwen-Image 2.1 Turbo
Since Qwen 2.1 Turbo dropped suddenly right after my last taste test, figured might as well do one for it as well.
Proof1 community thread
Key points
- Each image is either Krea2-Turbo or Qwen 2.1 Turbo, using the exact same prompt.
- You can also guess which one of each is Krea2 or Qwen 2.1 Turbo.
- Krea2-Turbo was the fp8 model and text encoder, but Qwen was BF16 for both model and text encoder.
- I did test (and have in the past) different samplers and schedulers in Krea2 but overall they generally seem to all be equal, so I did not differ from the standard Euler-Simple.
Sources (1)
- [1]A/B Blind Taste Test - Krea2-Turbo vs. Qwen-Image 2.1 Turbor/StableDiffusion (top, day) · Oct 11, 10:22 PM
Since Qwen 2.1 Turbo dropped suddenly right after my last taste test, figured might as well do one for it as well.
Each image is either Krea2-Turbo or Qwen 2.1 Turbo, using the exact same prompt.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 11, 2026Agents That Own Their Inference — Du'an Lightfoot & Khaja Omer, Akamai Technologies
- Oct 10, 2026Benefits of using bigger models than Qwen 3.8 flash next?
- Oct 10, 2026Engineer / developer observations of Gemma4-31B, Qwen3.8-27B, and 6.1-Sol for software engineering work
- Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
- Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
- Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0
