kapibala

打印出来的结果如下： accuracy of int8 model is: 0.977000 accuracy of fp32 model is: 0.977000 int8-model test time is 1.8347067832946777 float-model test time is 0.36646580696105957 Size of mnist_model_example_optimized.onnx: 439206 bytes Size of...

为什么Qwen_Image的推理代码里面的text_encoder部分和modelscope以及huggingface里面的text_encoder的权重中的key值对不上？

3

我采用下面的代码来单次推理Qwen_image: ``` import glob from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig from PIL import Image import torch import os os.environ["PYTHONBREAKPOINT"] = "0" pipe = QwenImagePipeline.from_pretrained( torch_dtype=torch.bfloat16, device="cuda", model_configs=[ ModelConfig(path=['/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00001-of-00004.safetensors', '/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00002-of-00004.safetensors', '/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00003-of-00004.safetensors', '/mnt/dolphinfs/hdd_pool/docker/user/hadoop-automaterials/yongzhao41/insert-anything/checkpoints/Qwen-Image/text_encoder/model-00004-of-00004.safetensors']),...