Text-to-Image
Diffusers
Safetensors
English
Chinese
Russian
QwenImage21Pipeline
image-editing
qwen-image
orbitquant
w4a4
4-bit precision
quantized
turbo
few-step
8-bit precision
Instructions to use WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4", 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
Download benchmark/orbitquant_staged.summary.json from WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4: direct link, hf CLI and curl.
- Browser
- Download file 1.07 kB
-
https://huggingface.co/WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4/resolve/main/benchmark/orbitquant_staged.summary.json
- Command line
-
hf download hf://WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4/benchmark/orbitquant_staged.summary.json
-
curl -L -o orbitquant_staged.summary.json https://huggingface.co/WaveCut/Turbo-Image-2.1-OrbitQuant-W4A4/resolve/main/benchmark/orbitquant_staged.summary.json
1.07 kB
| { | |
| "label": "orbitquant_staged", | |
| "mode": "staged", | |
| "quantized": true, | |
| "gpu": "NVIDIA GeForce RTX 5090", | |
| "torch": "2.8.0+cu128", | |
| "cuda": "12.8", | |
| "python": "3.12.3", | |
| "baseline_nvml_gib": 0.4864501953125, | |
| "jobs": [ | |
| "00-studio-product", | |
| "01-human-portrait", | |
| "02-mucha-poster", | |
| "03-hokusai-wave", | |
| "04-bauhaus-risograph", | |
| "05-technical-cutaway", | |
| "06-long-latin-text", | |
| "07-long-cyrillic-text", | |
| "08-mixed-diagram", | |
| "09-wide-city-scene" | |
| ], | |
| "load_cpu_s": 1.4314896063879132, | |
| "te_to_gpu_s": 1.1430589817464352, | |
| "te_peak_nvml_gib": 8.95538330078125, | |
| "te_peak_torch_gib": 7.857428550720215, | |
| "dit_vae_to_gpu_s": 0.7595742871053517, | |
| "dit_peak_nvml_gib": 13.40069580078125, | |
| "dit_peak_torch_gib": 11.470617771148682, | |
| "hot_medians": { | |
| "1024": { | |
| "total_s": 2.121799952350557, | |
| "encode_s": 0.07719557080417871, | |
| "denoise_s": 1.815999576356262, | |
| "decode_s": 0.22877847496420145, | |
| "dit_vae_s": 2.0447780513204634, | |
| "cold_first_total_s": 3.018771235831082, | |
| "n_hot": 20 | |
| } | |
| } | |
| } | |