IntelGpu-ComfyUI-Collection

每份档案 = 一次执行的完整上下文:运行环境、模型加载、时间轴、原始日志、工作流结构、产物


← 返回档案列表

202611031216_Moss文生图8步+TE2b优化

2026-11-03 12:16:05 · sess-20261103-105303 · 工作流 Moss
success重载omnixpu加速B58016G
总耗时
111.89s
采样耗时
32s
采样步数
8 / 8
每步采样
4.07s/it
模型载入
8.10GB
单次峰值
5.04GB

生成物

Moss-20261103121605_00001_.png
Moss-20261103121605_00002_.png
Moss-20261103121605_00003_.png
共 3 张产物 · 同一次执行 · 点图右下角数字切换,右侧信息跟着变
文件名
Moss-20261103121605_00001_.png
同目录副本
202611031216_Moss文生图8步+TE2b优化_1.png
类型
image
分辨率
1296 × 976
像素数
1,264,896(1.26 MP)
大小
1.4 MB
修改时间
2026-11-03 12:41:25
batch 序号
0
指纹
a38c961112745eac… (sha256 · 64 位,点开看全文)a38c961112745eacf9bc51f28211e9783c0f4e2b55a4b632edf699e3641def86
来源节点
#12
文件名
Moss-20261103121605_00002_.png
同目录副本
202611031216_Moss文生图8步+TE2b优化_2.png
类型
image
分辨率
1296 × 976
像素数
1,264,896(1.26 MP)
大小
1.4 MB
修改时间
2026-11-03 12:41:25
batch 序号
1
指纹
e2b767d427b591a2… (sha256 · 64 位,点开看全文)e2b767d427b591a2fefc00afb1365294f9af50cb9344a3d9eab87a0e0ce8c9fe
来源节点
#12
文件名
Moss-20261103121605_00003_.png
同目录副本
202611031216_Moss文生图8步+TE2b优化_3.png
类型
image
分辨率
1296 × 976
像素数
1,264,896(1.26 MP)
大小
1.5 MB
修改时间
2026-11-03 12:41:25
batch 序号
2
指纹
b3c6bb5382dab6ea… (sha256 · 64 位,点开看全文)b3c6bb5382dab6ea44d7d276a65df7cadbc547d5a48ee47a5d9d10873eb5d27f
来源节点
#12

模型加载模型文件 / 加载节点来自工作流结构(API 图);载入 MB / 耗时 / MB/s / 路径来源来自执行日志

角色模型文件加载节点载入 MB耗时 sMB/s路径来源
底模 basemoss_image_sft_int8_convrot.safetensors ext/moss_image_sft_int8_convrot.safetensors#1 UNETLoader MOSSImage5162.841.243125policy 相邻
文本编码器 text_encoderqwen3.5-2b_int8_linear.safetensors#3 MossCLIPLoader————
文本编码器 text_encoderqwen3.5-2b-int8.safetensors ext/qwen3.5-2b-int8.safetensors#3 MossCLIPLoader Qwen35TEModel_2973.70.08037172policy 相邻
VAE vaeflux2-vae.safetensors#4 VAELoader AutoencoderKL160.30.381421未识别
LoRA loraMOSS-Image-SFT-8-steps.safetensors Moss/MOSS-Image-SFT-8-steps.safetensors#2 LoraLoaderModelOnly————
共 5 行(图中每一处模型引用各占一行,不合并):3 行在执行日志里有载入数据,2 行只有结构引用。
MB/s 用于区分「内存回迁」(GB/s 级)与「磁盘重读」(数百 MB/s)。text_encoder 在某些栈上 device_to=cpu,它的加载耗时接近 0,不代表省了显存搬运。

工作流结构UI 图含 bypass 节点,API 图是真正执行的子集导出

画布节点数(UI 图)13
实际执行节点数(API 图)13
节点状态分布(UI 图 mode)active 13 · muted 0 · bypassed 0
被 bypass 的节点无
被 mute 的节点无
节点详情 13 个节点 · 4 个插件
节点名插件名插件版本
CLIPTextEncode 负面提示词comfy-core0.41.0
CLIPTextEncode 提示词comfy-core0.41.0
EmptyLatentImage 空Latent图像comfy-core0.41.0
KSampler K采样器comfy-core0.41.0
LoraLoaderModelOnly LoRA加载器(仅模型)comfy-core0.41.0
ResolutionSelector 分辨率选择器comfy-core0.41.0
SaveImage 保存图像comfy-core0.41.0
UNETLoader UNet加载器comfy-core0.41.0
VAEDecode VAE解码comfy-core0.41.0
VAELoader 加载VAEcomfy-core0.41.0
LogCollectionComfyUI-FullLog—
MossCLIPLoader Load CLIP (MOSS + projection)moss-image-mini-encoder 1cyberlangke1ee1855e5a699…
Seed (rgthree)rgthree-comfy8ff50e452188…

运行环境

系统Windows-11-10.0.22000-SP0 · AMD64 · build 10.0.22000
物理内存15.9 GB (16G)
GPUIntel(R) Arc(TM) B580 Graphics (0xE20B, 11946.2 MB, driver 1.17.39894+4)
平台Intel(R) oneAPI Unified Runtime over Level-Zero V2
计算单元160
Python3.13.11
torch2.15.0+xpu (xpu available: True, devices: 1)
ComfyUI0.43.1 preview=Latent2RGB
插件数67
加速栈
加速方案omnixpu加速 (工作流执行日志中 omni_xpu_kernel 0.2.0b3+torch215.bmg 生效,且出现 [OmniXPU] 插件标记)
OmniXPU 内核omni_xpu_kernel 0.2.0b3+torch215.bmg 已生效:sdp, norm, rotary, linear_fp8, int8, layout
OmniXPU 插件ComfyUI-OmniXPU 15 个 adapter applied、4 个 skipped
aimdocomfy-aimdo 0.6.0 未启用 (disabled by env)
kitchen XPUcomfy-kitchen 0.2.40 xpu 后端可用 (adaln, apply_rope, apply_rope1, apply_rope1_… 共 50 项)
加速方案 = 内核生效行 + 插件 [OmniXPU] 标记,两处都在工作流执行日志里才判「omnixpu加速」;aimdo / kitchen 是可选栈,不影响方案判定,也不进文件名。
运行时环境变量 17 项
变量名值
OCL_ICD_FILENAMES;F:\Intel-oneAPI\compiler\latest\bin\intelocl64.dll
OMNIXPU_DEBUG0
OMNIXPU_ENABLE1
ONEAPI_CLANG_VERSION22
ONEAPI_DEVICE_SELECTORlevel_zero:0
ONEAPI_PATHF:\Intel-oneAPI
ONEAPI_ROOTF:\Intel-oneAPI
SYCL_CACHE_MAX_SIZE8192
SYCL_CACHE_THRESHOLD7
SYCL_DEVICE_FILTERlevel_zero
SYCL_PI_LEVEL_ZERO_DEVICE_SCOPE_EVENTS0
SYCL_PI_LEVEL_ZERO_TRACK_INDIRECT_ACCESS_MEMORY1
SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS1
UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS1
UR_L0_USE_IMMEDIATE_COMMANDLISTS1
ZE_DEVICE_SLEEP0
ZE_ENABLE_PCI_ID_DEVICE_ORDER1

时间轴

时刻相对起点 s增量 s事件
12:16:06.7550.740.74下发存储策略 · qwen3.5-2b-int8.safetensors
12:16:20.12914.1213.38请求加载 Qwen35TEModel_
12:16:20.20914.200.08qwen3.5-2b-int8.safetensors 就绪(2973.72 MB)
12:16:36.37130.3616.16下发存储策略 · moss_image_sft_int8_convrot.safetensors
12:16:36.56030.550.19请求加载 MOSSImage
12:17:17.80371.7941.24moss_image_sft_int8_convrot.safetensors 就绪(5162.83 MB)
12:17:51.531105.5233.73请求加载 AutoencoderKL
12:17:51.912105.900.38AutoencoderKL 就绪(160.31 MB)
12:17:57.682111.675.77执行完成

原始日志内嵌,不依赖 user/comfyui.log

来源 comfyui.log · 24 行 · 日志自报耗时 111.89 s
原始日志全文
[2026-11-03 12:16:06.012] Found quantization metadata version 1[2026-11-03 12:16:06.013] Using MixedPrecisionOps for text encoder[2026-11-03 12:16:06.755] Model storage policy: fast_disk=False paths=['E:\\model\\qwen3.5-2b-int8.safetensors'][2026-11-03 12:16:20.129] Requested to load Qwen35TEModel_[2026-11-03 12:16:20.209] loaded completely;  2973.72 MB loaded, full load: True[2026-11-03 12:16:20.226] CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16[2026-11-03 12:16:36.353] Found quantization metadata version 1[2026-11-03 12:16:36.353] Detected mixed precision quantization[2026-11-03 12:16:36.354] Using mixed precision operations[2026-11-03 12:16:36.354] Native ops: int8_tensorwise , emulated ops: mxfp8, w6a8_int8, float8_e5m2, nvfp4, float8_e4m3fn, convrot_w4a4, asym_w4a8_int8[2026-11-03 12:16:36.368] model weight dtype torch.bfloat16, manual cast: torch.bfloat16[2026-11-03 12:16:36.370] model_type FLOW[2026-11-03 12:16:36.371] Model storage policy: fast_disk=False paths=['E:\\model\\moss_image_sft_int8_convrot.safetensors'][2026-11-03 12:16:36.506] [OmniXPU] LoRA memory budget cached: source=1134.2MiB/756 tensors model_added=1134.0MiB model_budget=1134.0MiB clip_added=0.0MiB clip_budget=0.0MiB[2026-11-03 12:16:36.559] [OmniXPU] LoRA model budget applied: cached=1134.0MiB/504 tensors requested=8656.6->9790.6MiB minimum=4328.3->5462.3MiB xpu_memory=available xpu_allocated=166.9MiB xpu_reserved=172.0MiB xpu_free=8776.5MiB xpu_total=11946.2MiB[2026-11-03 12:16:36.560] Requested to load MOSSImage[2026-11-03 12:17:17.803] loaded completely; 5459.38 MB usable, 5162.83 MB loaded, full load: True[2026-11-03 12:17:17.887] [OmniXPU] LoRA model load complete: xpu_memory=available xpu_allocated=5163.3MiB xpu_reserved=5366.0MiB xpu_free=3686.5MiB xpu_total=11946.2MiB[2026-11-03 12:17:50.618] 100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:32<00:00,  3.72s/it]100%|██████████████████████████████████████████████████████████████████████████████████████████████████| 8/8 [00:32<00:00,  4.07s/it][2026-11-03 12:17:51.531] Requested to load AutoencoderKL[2026-11-03 12:17:51.912] loaded completely; 5667.06 MB usable, 160.31 MB loaded, full load: True[2026-11-03 12:17:57.682] Prompt executed in 111.89 seconds