PowerPaint
PowerPaint copied to clipboard
[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model....
数据集训练
您好,想请问一下,该代码是否支持自制数据集的训练与测试?如果支持该如何进行训练配置呢?
你好,我是调用ppt-v2-1这个里面的模型,然后我想把整个代码都放在指定的gpu上,但是我在主代码中将模型放在指定的gpu上,后面导入外部模型开始运行后还是修改在默认gpu上,如何修改代码或者做其他操作,让整体包括过程中所有代码在指定gpu上?
for more stable generator. and for speed infer, can reference (lora, lcm) + [trt](https://github.com/NVIDIA/TensorRT/blob/release/10.5/demo/Diffusion/flux_pipeline.py)
My cuda memory size is only 16G,can it run for training?
Almost got this running on Apple Silicon but it fails with multiple references to cuda which is unsupported on Apple GPUs. PyTorch is [capable of running on CPU](https://eitca.org/artificial-intelligence/eitc-ai-dlpp-deep-learning-with-python-and-pytorch/data-eitc-ai-dlpp-deep-learning-with-python-and-pytorch/datasets/can-pytorch-run-on-a-cpu/) and I've...
pip Could not find a version that satisfies the requirement petrel_client,How to install petrel_client?
at dev brach, init pipeline as following code, but the output image is covered with a red layer `# brushnet-based version unet = UNet2DConditionModel.from_pretrained( "stable-diffusion-v1-5/stable-diffusion-v1-5", subfolder="unet", revision=None, torch_dtype=weight_dtype, ) text_encoder...
@zengyh1900 我下载的laion数据集,每一张图会对应一个json  问题1:你的laion数据集中,随机mask对应的提示词是上面json里面的caption吗? 问题2:如果是,我理解anno_info["remark"]是对应上面json,为什么prompt来自anno_info["content"],而不是来自remark 问题3:如果不是,anno_info["content"]是怎么来的,我理解随机mask对应的提示词是不是也得通过blip来获取? 问题4:可以提供几个样本和对应的annotation文件吗或者有一个文档能解释一下每一个文件的意义和构建来源,以及每一个字段的意义?方便我们清晰地知道你的数据结构是什么样的。 
 两边很容易出现墙、框、之类的遮挡,请问怎么解决
NSFW
 https://huggingface.co/CompVis/stable-diffusion-v1-4/discussions/25