Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
SeaWolf-AIΒ 
posted an update 3 days ago
Post
3658
πŸ–ΌοΈ NO GPU, Only CPU : Z-Image model

Zero graphics cards. 46 seconds. Photoreal.

That laptop you're reading this on. No graphics card, right? It generates images.

No CUDA install. No Python environment. No driver changes. One binary, three model files. Done.

πŸ“Š Measured β€” GPU count used: zero

512Γ—512 : 46.4 s
Korean prompt : 45.3 s (faster than English)
1024Γ—1024 : 192.7 s
Peak RAM : 6.42 GB
GPUs used : 0

(Intel Xeon Gold 6526Y Γ—2, 48 threads, Q4_0, 3 steps)

⚑ From 244 seconds to 46 β€” 5.3Γ—

Run it on defaults and it takes 244 s. Switch to 3 steps and it's 48.6 s. Add VAE tiling and it's 46.4 s.

The biggest culprit was the default. Z-Image Turbo is distilled to paint in few strokes, but the tool's default is 20. We were throwing away 5Γ— for no reason. So were we, at first.

3 is the floor. Put 4 and 3 side by side and you cannot tell them apart. At 2 it collapses β€” water droplets and wood grain vanish, and the surface turns cloth-like.

πŸ”— Links

Model
FINAL-Bench/POCKET-Zimage-CPU

Live demo Space (runs on CPU)
FINAL-Bench/POCKET-Zimage-CPU

POCKET collection
FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6

create a photo of 3 kids looking straight and standing on their right legs and raising their right hand

This is very interesting thank you but also two server grade cpus worth 4k generating such a small image using a tiny quantized model taking that long is not too useable