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
Download examples/benchmark.json from HelloSun/Z-Image-Turbo-OpenVINO-INT4: direct link, hf CLI and curl.
- Browser
- Download file 10.3 kB
-
https://huggingface.co/HelloSun/Z-Image-Turbo-OpenVINO-INT4/resolve/main/examples/benchmark.json
- Command line
-
hf download hf://HelloSun/Z-Image-Turbo-OpenVINO-INT4/examples/benchmark.json
-
curl -L -o benchmark.json https://huggingface.co/HelloSun/Z-Image-Turbo-OpenVINO-INT4/resolve/main/examples/benchmark.json
10.3 kB
| { | |
| "model": "z-image-turbo-ov-int4", | |
| "load_compile_s": 7.72, | |
| "height": 1024, | |
| "width": 1024, | |
| "results": [ | |
| { | |
| "id": "01_hanfu_portrait", | |
| "prompt": "Young Chinese woman in red Hanfu, intricate embroidery, impeccable makeup, red floral forehead pattern, elaborate high bun, golden phoenix headdress, soft-lit outdoor night background, silhouetted tiered pagoda, blurred colorful distant lights, photorealistic, ultra detailed, 8k", | |
| "seed": 42, | |
| "height": 1024, | |
| "width": 1024, | |
| "num_inference_steps_param": 9, | |
| "scheduler_steps_observed": 9, | |
| "step_times_s": [ | |
| 17.968, | |
| 12.199, | |
| 11.943, | |
| 12.37, | |
| 11.715, | |
| 12.203, | |
| 12.084, | |
| 12.277, | |
| 11.501 | |
| ], | |
| "total_s": 116.19, | |
| "mean_step_s": 12.696, | |
| "rss_before_gb": 2.803, | |
| "rss_after_gb": 16.306, | |
| "image": "01_hanfu_portrait_seed42_8step_1024.png", | |
| "control_512": { | |
| "image": "01_hanfu_portrait_seed42_8step_512.png", | |
| "height": 512, | |
| "width": 512, | |
| "total_s": 38.72, | |
| "mean_step_s": 4.236, | |
| "step_times_s": [ | |
| 8.849, | |
| 3.495, | |
| 3.596, | |
| 3.694, | |
| 4.091, | |
| 3.598, | |
| 3.688, | |
| 3.601, | |
| 3.513 | |
| ] | |
| } | |
| }, | |
| { | |
| "id": "02_astronaut_jungle", | |
| "prompt": "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k, photorealistic, cinematic lighting", | |
| "seed": 43, | |
| "height": 1024, | |
| "width": 1024, | |
| "num_inference_steps_param": 9, | |
| "scheduler_steps_observed": 9, | |
| "step_times_s": [ | |
| 12.932, | |
| 12.164, | |
| 11.53, | |
| 11.87, | |
| 11.919, | |
| 12.334, | |
| 12.157, | |
| 12.026, | |
| 12.078 | |
| ], | |
| "total_s": 110.82, | |
| "mean_step_s": 12.112, | |
| "rss_before_gb": 16.306, | |
| "rss_after_gb": 16.313, | |
| "image": "02_astronaut_jungle_seed43_8step_1024.png", | |
| "control_512": { | |
| "image": "02_astronaut_jungle_seed43_8step_512.png", | |
| "height": 512, | |
| "width": 512, | |
| "total_s": 33.04, | |
| "mean_step_s": 3.617, | |
| "step_times_s": [ | |
| 4.963, | |
| 3.599, | |
| 3.474, | |
| 3.308, | |
| 3.301, | |
| 3.394, | |
| 3.512, | |
| 3.584, | |
| 3.416 | |
| ] | |
| } | |
| }, | |
| { | |
| "id": "03_taipei_cyberpunk", | |
| "prompt": "Cyberpunk street in Taipei at night, heavy rain, neon signs with text 'TAIPEI' and Chinese characters '台北', reflections on wet asphalt, crowded night market, cinematic, ultra detailed", | |
| "seed": 44, | |
| "height": 1024, | |
| "width": 1024, | |
| "num_inference_steps_param": 9, | |
| "scheduler_steps_observed": 9, | |
| "step_times_s": [ | |
| 13.598, | |
| 12.205, | |
| 12.0, | |
| 12.133, | |
| 12.003, | |
| 11.876, | |
| 11.499, | |
| 11.602, | |
| 11.68 | |
| ], | |
| "total_s": 110.31, | |
| "mean_step_s": 12.066, | |
| "rss_before_gb": 16.313, | |
| "rss_after_gb": 16.315, | |
| "image": "03_taipei_cyberpunk_seed44_8step_1024.png", | |
| "control_512": { | |
| "image": "03_taipei_cyberpunk_seed44_8step_512.png", | |
| "height": 512, | |
| "width": 512, | |
| "total_s": 31.81, | |
| "mean_step_s": 3.489, | |
| "step_times_s": [ | |
| 4.58, | |
| 3.399, | |
| 3.501, | |
| 3.235, | |
| 3.084, | |
| 3.219, | |
| 3.364, | |
| 3.417, | |
| 3.6 | |
| ] | |
| } | |
| }, | |
| { | |
| "id": "04_shiba_astronaut", | |
| "prompt": "Cute Shiba Inu wearing a tiny astronaut helmet, sitting in a field of sunflowers under a starry sky, dreamy illustration, vibrant colors, high quality", | |
| "seed": 45, | |
| "height": 1024, | |
| "width": 1024, | |
| "num_inference_steps_param": 9, | |
| "scheduler_steps_observed": 9, | |
| "step_times_s": [ | |
| 12.608, | |
| 11.887, | |
| 11.919, | |
| 11.788, | |
| 11.792, | |
| 11.993, | |
| 12.014, | |
| 11.593, | |
| 11.894 | |
| ], | |
| "total_s": 109.3, | |
| "mean_step_s": 11.943, | |
| "rss_before_gb": 16.315, | |
| "rss_after_gb": 16.32, | |
| "image": "04_shiba_astronaut_seed45_8step_1024.png", | |
| "control_512": { | |
| "image": "04_shiba_astronaut_seed45_8step_512.png", | |
| "height": 512, | |
| "width": 512, | |
| "total_s": 31.05, | |
| "mean_step_s": 3.396, | |
| "step_times_s": [ | |
| 4.37, | |
| 3.373, | |
| 3.322, | |
| 3.572, | |
| 3.316, | |
| 2.994, | |
| 3.002, | |
| 3.201, | |
| 3.411 | |
| ] | |
| } | |
| }, | |
| { | |
| "id": "05_ink_landscape", | |
| "prompt": "Traditional Chinese ink wash landscape, misty mountains, a small pagoda on a cliff, cranes flying, minimalist, elegant, high aesthetic quality", | |
| "seed": 46, | |
| "height": 1024, | |
| "width": 1024, | |
| "num_inference_steps_param": 9, | |
| "scheduler_steps_observed": 9, | |
| "step_times_s": [ | |
| 13.346, | |
| 11.917, | |
| 11.673, | |
| 11.505, | |
| 11.7, | |
| 11.399, | |
| 11.917, | |
| 12.095, | |
| 11.913 | |
| ], | |
| "total_s": 109.26, | |
| "mean_step_s": 11.941, | |
| "rss_before_gb": 16.32, | |
| "rss_after_gb": 16.325, | |
| "image": "05_ink_landscape_seed46_8step_1024.png", | |
| "control_512": { | |
| "image": "05_ink_landscape_seed46_8step_512.png", | |
| "height": 512, | |
| "width": 512, | |
| "total_s": 32.69, | |
| "mean_step_s": 3.587, | |
| "step_times_s": [ | |
| 4.572, | |
| 3.411, | |
| 3.513, | |
| 3.608, | |
| 3.468, | |
| 3.399, | |
| 3.411, | |
| 3.492, | |
| 3.405 | |
| ] | |
| } | |
| } | |
| ], | |
| "sysinfo": { | |
| "cpu_model": "Intel(R) Xeon(R) Platinum 8559C", | |
| "arch": "x86_64", | |
| "sockets": 2, | |
| "cores_per_socket": 48, | |
| "threads_per_core": 2, | |
| "vcpus": 192, | |
| "os_cpu_count": 192, | |
| "lscpu": "Architecture: x86_64\nCPU op-mode(s): 32-bit, 64-bit\nAddress sizes: 46 bits physical, 48 bits virtual\nByte Order: Little Endian\nCPU(s): 192\nOn-line CPU(s) list: 0-191\nVendor ID: GenuineIntel\nModel name: Intel(R) Xeon(R) Platinum 8559C\nCPU family: 6\nModel: 207\nThread(s) per core: 2\nCore(s) per socket: 48\nSocket(s): 2\nStepping: 2\nBogoMIPS: 4800.00\nFlags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd ida arat avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq rdpid cldemote movdiri movdir64b md_clear serialize amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities\nHypervisor vendor: KVM\nVirtualization type: full\nL1d cache: 4.5 MiB (96 instances)\nL1i cache: 3 MiB (96 instances)\nL2 cache: 192 MiB (96 instances)\nL3 cache: 640 MiB (2 instances)\nNUMA node(s): 2\nNUMA node0 CPU(s): 0-47,96-143\nNUMA node1 CPU(s): 48-95,144-191\nVulnerability Gather data sampling: Not affected\nVulnerability Ghostwrite: Not affected\nVulnerability Indirect target selection: Not affected\nVulnerability Itlb multihit: Not affected\nVulnerability L1tf: Not affected\nVulnerability Mds: Not affected\nVulnerability Meltdown: Not affected\nVulnerability Mmio stale data: Not affected\nVulnerability Old microcode: Not affected\nVulnerability Reg file data sampling: Not affected\nVulnerability Retbleed: Not affected\nVulnerability Spec rstack overflow: Not affected\nVulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl\nVulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization\nVulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S\nVulnerability Srbds: Not affected\nVulnerability Tsa: Not affected\nVulnerability Tsx async abort: Not affected\nVulnerability Vmscape: Not affected\n", | |
| "openvino_version": "2026.4.0-22959-99c81491cc3-releases/2026/4", | |
| "openvino_devices": [ | |
| "CPU" | |
| ], | |
| "packages": { | |
| "diffusers": "0.37.1", | |
| "transformers": "4.57.6", | |
| "tokenizers": "0.22.0", | |
| "huggingface-hub": "0.35.1", | |
| "optimum": "2.3.0", | |
| "optimum-intel": "2.2.0", | |
| "openvino": "2026.4.0", | |
| "nncf": "3.4.0", | |
| "torch": "2.14.0", | |
| "pillow": "12.3.0", | |
| "psutil": "7.2.2" | |
| }, | |
| "model_sizes_GB": { | |
| "fp16_transformer_GB": 12.31, | |
| "int4_transformer_GB": 3.199, | |
| "fp16_text_encoder_GB": 7.843, | |
| "int4_text_encoder_GB": 2.237, | |
| "fp16_vae_decoder_GB": 0.099, | |
| "int4_vae_decoder_GB": 0.05, | |
| "fp16_vae_encoder_GB": 0.069, | |
| "int4_vae_encoder_GB": 0.034 | |
| }, | |
| "ram_note": "2.0Ti total, avail ~585-757Gi during runs, Swap 1.6Ti", | |
| "settings": "num_inference_steps=9 (8x DiT forwards), guidance_scale=0.0, OVDiffusionPipeline.from_pretrained(INT4,compile=True), CPU only" | |
| } | |
| } | |