When using xpu backend, stable diffusion give bad result (comparing with 'cpu' backend and also opevino)

Describe the bug

Hi, I noticed that when I am using intel-extension-for-pytorch, it seems stable diffusion just doesn't care about my full prompt and the generated picuture is quiet bad quality. I have a minimal case to show this. Here is the code to generate a picture , if I change to use cpu backend, I got a much better output. Also the output is consistent with the output if I am using openvino with their GPU backend.

#!/home/leptonwu/venv_ipex/bin/python
import time
import torch
import intel_extension_for_pytorch
from diffusers import StableDiffusionPipeline

torch.manual_seed(0)
device = "xpu"
pipe = StableDiffusionPipeline.from_single_file("realisticVisionV60B1_v51HyperVAE.safetensors").to(device)
start = time.time()
image = pipe("a man eating apple", guidance_scale=1.5,
                width=512, height=512, num_inference_steps=6)
image.images[0].save("out-ipex-%s.jpg" % device)
print(time.time() - start)

out-ipex-xpu out-ipex-cpu

Versions

Collecting environment information... PyTorch version: 2.3.1+cxx11.abi PyTorch CXX11 ABI: Yes IPEX version: 2.3.110+xpu IPEX commit: 95c945927 Build type: Release

OS: Debian GNU/Linux 12 (bookworm) (x86_64) GCC version: (Debian 12.2.0-14) 12.2.0 Clang version: N/A IGC version: N/A CMake version: version 3.25.1 Libc version: glibc-2.36

Python version: 3.11.2 (main, Aug 26 2024, 07:20:54) [GCC 12.2.0] (64-bit runtime) Python platform: Linux-6.10.6+bpo-amd64-x86_64-with-glibc2.36 Is XPU available: True DPCPP runtime version: N/A MKL version: N/A GPU models and configuration: [0] _XpuDeviceProperties(name='Intel(R) Arc(TM) A580 Graphics', platform_name='Intel(R) Level-Zero', type='gpu', driver_version='1.3.29735', total_memory=7721MB, max_compute_units=384, gpu_eu_count=384, gpu_subslice_count=24, max_work_group_size=1024, max_num_sub_groups=128, sub_group_sizes=[8 16 32], has_fp16=1, has_fp64=0, has_atomic64=1) Intel OpenCL ICD version: 24.22.29735.27-914~22.04 Level Zero version: 1.3.29735.27-914~22.04

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 43 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 16 On-line CPU(s) list: 0-15 Vendor ID: AuthenticAMD Model name: AMD Ryzen 7 3700X 8-Core Processor CPU family: 23 Model: 113 Thread(s) per core: 2 Core(s) per socket: 8 Socket(s): 1 Stepping: 0 Frequency boost: enabled CPU(s) scaling MHz: 86% CPU max MHz: 4426.1709 CPU min MHz: 2200.0000 BogoMIPS: 7199.56 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl rdpid overflow_recov succor smca sev sev_es Virtualization: AMD-V L1d cache: 256 KiB (8 instances) L1i cache: 256 KiB (8 instances) L2 cache: 4 MiB (8 instances) L3 cache: 32 MiB (2 instances) NUMA node(s): 1 NUMA node0 CPU(s): 0-15 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection Vulnerability Spec rstack overflow: Mitigation; Safe RET Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

Versions of relevant libraries: [pip3] dctorch==0.1.2 [pip3] intel_extension_for_pytorch==2.3.110+xpu [pip3] numpy==1.26.4 [pip3] open_clip_torch==2.26.1 [pip3] pytorch-lightning==1.9.4 [pip3] torch==2.3.1+cxx11.abi [pip3] torchdiffeq==0.2.4 [pip3] torchmetrics==1.4.2 [pip3] torchsde==0.2.6 [pip3] torchvision==0.18.1+cxx11.abi [conda] N/A

intel / intel-extension-for-pytorch

When using xpu backend, stable diffusion give bad result (comparing with 'cpu' backend and also opevino) #713

Describe the bug

Versions