Same scene, 30 art styles, 8 local models on a Mac (mflux): Qwen-Image 2.1, FLUX.2 Klein, Krea 2, Z-Image, Ming-Image, FIBO 1.5, ERNIE, Boogu
I got into text-to-image when Qwen-Image 2.1 came out, and started playing with it on my Mac with mflux 0.22.
Proof1 community thread
Key points
- I was impressed by how many art styles it could pull off, so I ran one simple prompt through it with only the art style changed, 30 times.
- Then I got curious how the other models would handle the same 30 styles.
- I like Qwen-Image 2.1 best, though I may be biased since it's what got me started.
- Qwen-Image 2.1 25, step cache 0.4 ~53 s
Sources (1)
- [1]Same scene, 30 art styles, 8 local models on a Mac (mflux): Qwen-Image 2.1, FLUX.2 Klein, Krea 2, Z-Image, Ming-Image, FIBO 1.5, ERNIE, Boogur/StableDiffusion (top, day) · Oct 12, 09:00 AM
I got into text-to-image when Qwen-Image 2.1 came out, and started playing with it on my Mac with mflux 0.22.
I was impressed by how many art styles it could pull off, so I ran one simple prompt through it with only the art style changed, 30 times.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 12, 2026AI Image alignment solution for Qwen Image 2.1 Edits
- Oct 11, 2026MCP - Qwen2.1 Turbo + Kandinsky Lite Video Gen on 8GB VRAM
- Oct 10, 2026Krea2 Turbo Distill 2 step LoRA - FINAL checkpoint released (chk51195)
- 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, 2026Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards
