ppdk-data

The detected CUDA version (10.1) mismatches the version that was used to compile PyTorch (10.2). Please make sure to use the same CUDA versions.

import torch from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, AutoPipelineForText2Image prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" pipe = StableDiffusionXLPipeline.from_pretrained( "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=False, local_files_only=False )...

Cell In[12], line 7 5 version = "zh-clip-vit-roberta-large-patch14" 6 model = ZhCLIPModel.from_pretrained(version) ----> 7 processor = ZhCLIPProcessor.from_pretrained(version) File ~/.conda/envs/diffuser_python/lib/python3.9/site-packages/transformers/processing_utils.py:184, in ProcessorMixin.from_pretrained(cls, pretrained_model_name_or_path, **kwargs) 153 @classmethod 154 def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):...

OSError: Can't load tokenizer for 'stabilityai/stable-diffusion-xl-base-1.0'

4

### Describe the bug **code is :** #DiffusionPipeline import torch from diffusers import StableDiffusionXLPipeline, StableDiffusionXLImg2ImgPipeline, AutoPipelineForText2Image prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" #加载SDXL...

where is the rcnn_bboxes come from?

6

where is the rcnn_bboxes come from?

question about the paper and model

2

Hello, i have a question about the paper and model. To generate the cropping result of the aspect ratio, it is necessary to create several candidate boxes by myself? The...

运行下载模型脚本时，报下面错误

2

 

kolors训练的loss显示为nan

1