Text-to-Image
Diffusers
OpenVINO
StableDiffusionXLPipeline
int4
optimum
optimum-intel
nncf
lcm
anime
sdxl
cpu
8-step
Instructions to use HelloSun/nova_xl_lcm-OpenVINO-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use HelloSun/nova_xl_lcm-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/nova_xl_lcm-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
26 days ago
-
docs: restructure README/REPORT and clean metadata
- README: add TOC, badges-free quick facts, unified zh-TW wording, per-example prompt blocks, benchmark summary tables, repo file map, known limitations and license section - README: add diffusers model-index frontmatter so HF renders model metadata - REPORT: convert dense bullet lists into proper tables, add TOC, per-step timings, and an observations/conclusions section - Fix benchmark numbers to match examples/benchmark.json - model_index.json: replace leaked local path in _name_or_path - examples/benchmark.json: use repo id and repo-relative image paths - examples/prompts.txt: strip leftover timestamps - quantize_int4.py: replace hardcoded /tmp paths with argparse flags - generate5.py: drop dead module-level OUT_DIR528e807 -
Add Nova XL LCM OpenVINO INT4: model + 10 examples + README/REPORT/scripts
Verified signature9257645