Text-to-Image
Diffusers
OpenVINO
ZImagePipeline
int4
optimum
optimum-intel
nncf
z-image
transformer
cpu
Instructions to use HelloSun/Z-Image-Turbo-OpenVINO-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HelloSun/Z-Image-Turbo-OpenVINO-INT4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("HelloSun/Z-Image-Turbo-OpenVINO-INT4", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit History
25 days ago
-
docs: restructure README/REPORT and clean metadata
- README: add TOC, quick-facts table, install/usage/parameters, file map, known limitations and licence section; split the benchmarked examples from the un-benchmarked style gallery - README: report model sizes from the actual Git-LFS byte counts instead of rounded hand-written figures - README: state explicitly that document shift=3.0; correct sizes to 20.32 GB -> 5.52 GB; note 9 scheduler steps vs the upstream 8 NFE claim - REPORT: convert dense bullet lists into proper tables, add a TOC, per-step timings, and an observations section - Replace benchmark numbers that disagreed with the benchmark JSON - model_index.json / */config.json: replace leaked build-host paths with the upstream repo id - benchmark.json: use the HF repo id and repo-relative image paths - benchmark_quantization.json: drop local build directories - examples/prompts.txt: strip leftover timestamps - scripts: replace hardcoded /home/user/app and /tmp paths with relative defaults and the real repo ideab6841
26 days ago
-
Add Z-Image-Turbo OpenVINO INT4 (optimum, NNCF)
Verified signature7628675