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

202611112058_H3_image文生图+TE4b优化_omnixpu加速_B580_16G_冷启

2026-11-11 20:58:10 · sess-20261111-205736 · 工作流 minimax_h3_image_t2i
success冷启omnixpu加速B58016G
总耗时
173.93s
采样耗时
23s
采样步数
6 / 6
每步采样
3.94s/it
模型载入
14.20GB
单次峰值
8.59GB

生成物

minimax_h3_image_t2i_00001_.png
文件名
minimax_h3_image_t2i_00001_.png
同目录副本
202611112058_H3_image文生图+TE4b优化_omnixpu加速_B580_16G_冷启_1.png
类型
image
分辨率
1120 × 1120
像素数
1,254,400(1.25 MP)
大小
2.1 MB
修改时间
2026-11-11 21:00:57
batch 序号
0
指纹
e41b75b7f3c276e6… (sha256 · 64 位,点开看全文)e41b75b7f3c276e67423948a49411e45b4896749a213029bd362242def37c016
来源节点
#1

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 baseMiniMax-H3-Image-Pruned-Q3_K_M.gguf ext/H3_diff/MiniMax-H3-Image-Pruned-Q3_K_M.gguf#37 UnetLoaderGGUFAdvanced MiniMaxH3Image8791.867.092131未识别
文本编码器 text_encodermmh3-4b-ClipProj-v3.1.safetensors#25 ClipProjApply————
文本编码器 text_encoderqwen3vl_4b_int8_convrot.safetensors ext/qwen3vl_4b_int8_convrot.safetensors#29 CLIPLoader Qwen3VLTEModel_4633.30.10444551policy 相邻
VAE vaeminimax_h3_image_vae_fp16.safetensors H3_vae/minimax_h3_image_vae_fp16.safetensors#21 VAELoaderKJ MiniMaxH3ImageVAE1114.23.749297按角色匹配
共 4 行:底模 1 · 文本编码器 2 · VAE 1。模型文件 / 加载节点来自工作流结构(API 图)。载入 MB / 耗时 / MB/s 来自工作流执行日志(`Requested to load` → `loaded completely`);同一文件一次执行里加载多次时合并为一行、数值是累计值,相加仍等于 KPI 的「模型载入」。
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工作流导出

画布节点数(UI 图)14
实际执行节点数(API 图)14
节点状态分布(UI 图 mode)active 14 · muted 0 · bypassed 0
被 bypass 的节点无
被 mute 的节点无
节点详情 14 个节点 · 6 个插件
节点名插件名插件版本
CLIPLoader 加载CLIPcomfy-core0.42.5
ConditioningZeroOut 条件零化comfy-core0.45.2
KSampler K采样器comfy-core0.45.2
MiniMaxH3ImageConditioningcomfy-core0.45.2
PrimitiveStringMultiline Text (user_prompt)comfy-core0.45.2
ResolutionSelector 分辨率选择器comfy-core0.45.2
SaveImage 保存图像comfy-core0.45.2
VAEDecodeTiled VAE解码(分块)comfy-core0.11.1
ClipProjApplyComfyUI-ClipProj nicolab28c01ba8fb8f41…
LogCollectionComfyUI-FullLog—
UnetLoaderGGUFAdvancedComfyUI-GGUF-XPU analytics-zoo39671fe73117…
VAELoaderKJcomfyui-kjnodes50a0837f9aea…
VRAM_Debugcomfyui-kjnodes9b565354e32a…
VRAMCleanupcomfyui_memory_cleanup1.1.3

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)
ComfyUI0.45.2 preview=Latent2RGB
插件数68
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 16 个 adapter applied、4 个 skipped
aimdocomfy-aimdo 0.6.0 未启用 (disabled by env)
kitchen XPUcomfy-kitchen 0.2.41 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 18 项
变量名值
OCL_ICD_FILENAMES;F:\Intel-oneAPI\compiler\latest\bin\intelocl64.dll
OMNIXPU_DEBUG0
OMNIXPU_ENABLE1
OMNIXPU_QWEN_IMAGE21_QKV1
ONEAPI_CLANG_VERSION23
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
20:58:10.6400.270.27下发存储策略 · minimax_h3_image_vae_fp16.safetensors
20:58:17.2096.846.57下发存储策略 · qwen3vl_4b_int8_convrot.safetensors
20:58:17.3316.960.12请求加载 Qwen3VLTEModel_
20:58:17.4357.070.11qwen3vl_4b_int8_convrot.safetensors 就绪(4633.34 MB)
20:58:54.13343.7736.70请求加载 MiniMaxH3Image
21:00:01.225110.8667.09MiniMaxH3Image 就绪(8791.75 MB)
21:00:50.719160.3549.49请求加载 MiniMaxH3ImageVAE
21:00:54.468164.103.75minimax_h3_image_vae_fp16.safetensors 就绪(1114.23 MB)
21:01:04.218173.859.75执行完成

原始日志内嵌,不依赖 user/comfyui.log

来源 user/comfyui.log · 35 行 · 日志自报耗时 173.93 s
原始日志全文
[2026-11-11 20:58:10.368] gguf qtypes: F32 (320), Q3_K (208)[2026-11-11 20:58:10.399] model weight dtype torch.bfloat16, manual cast: None[2026-11-11 20:58:10.409] model_type FLOW[2026-11-11 20:58:10.424] Model storage policy: fast_disk=False paths=[][2026-11-11 20:58:10.640] Model storage policy: fast_disk=False paths=['E:\\model\\H3_vae\\minimax_h3_image_vae_fp16.safetensors'][2026-11-11 20:58:16.382] VAE load device: xpu:0, offload device: cpu, dtype: torch.float16[2026-11-11 20:58:16.841] Found quantization metadata version 1[2026-11-11 20:58:16.842] Using MixedPrecisionOps for text encoder[2026-11-11 20:58:17.209] Model storage policy: fast_disk=False paths=['E:\\model\\qwen3vl_4b_int8_convrot.safetensors'][2026-11-11 20:58:17.331] Requested to load Qwen3VLTEModel_[2026-11-11 20:58:17.435] loaded completely;  4633.34 MB loaded, full load: True[2026-11-11 20:58:17.458] CLIP/text encoder model load device: cpu, offload device: cpu, current: cpu, dtype: torch.float16[2026-11-11 20:58:17.536] [ClipProj] mmh3-4b-ClipProj-v3.1.safetensors | tap 24 | 2560 -> 5120 | cos_test 0.6874[2026-11-11 20:58:54.133] Requested to load MiniMaxH3Image[2026-11-11 21:00:01.225] loaded completely; 10103.00 MB usable, 8791.75 MB loaded, full load: True[2026-11-11 21:00:02.129] [OmniXPU] norm first use: RMSNorm shape=torch.Size([452, 5376])[2026-11-11 21:00:02.793] [OmniXPU] experimental capability-driven BMG D128 CUTE route enabled; set OMNI_ATTN_BACKEND=torch to disable it if this workflow shows an issue[2026-11-11 21:00:02.794] [OmniXPU] attention CUTE_BHLD_D128 #1: heads=56 q=452 kv=452 dtype=torch.bfloat16[2026-11-11 21:00:02.899] [OmniXPU] attention CUTE_BHLD_D128 #2: heads=56 q=452 kv=452 dtype=torch.bfloat16[2026-11-11 21:00:02.962] [OmniXPU] attention CUTE_BHLD_D128 #3: heads=56 q=452 kv=452 dtype=torch.bfloat16[2026-11-11 21:00:26.760] 100%|████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:23<00:00,  3.77s/it]100%|████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:23<00:00,  3.94s/it][2026-11-11 21:00:50.091] VRAM清理完成 [卸载模型: True, 清空缓存: True][2026-11-11 21:00:50.719] Requested to load MiniMaxH3ImageVAE[2026-11-11 21:00:54.468] loaded completely; 10103.00 MB usable, 1114.23 MB loaded, full load: True[2026-11-11 21:00:55.092] [OmniXPU] attention fallback: batch=4 (seq=261)[2026-11-11 21:00:55.802] [OmniXPU] attention fallback: batch=4 (seq=261)[2026-11-11 21:00:55.804] [OmniXPU] attention fallback: batch=4 (seq=261)[2026-11-11 21:00:55.806] [OmniXPU] attention fallback: batch=4 (seq=261)[2026-11-11 21:00:55.807] [OmniXPU] attention fallback: batch=4 (seq=261)[2026-11-11 21:00:56.390] VRAMdebug: free memory before: 11,346,875,904[2026-11-11 21:00:57.181] VRAMdebug: free memory after: 12,526,496,768[2026-11-11 21:00:57.181] VRAMdebug: freed memory: 1,179,620,864[2026-11-11 21:01:04.218] Prompt executed in 173.93 seconds