Zhen Li comments

Results 197 comments of


                                            Zhen Li

建议搞个百度网盘

https://civitai.com/models/139562?modelVersionId=268861

For those GPUs that do not support bfloat16, please change [this line](https://github.com/TencentARC/PhotoMaker/blob/6ec44fc13909d64a65c635b9e3b6f238eb1de9fe/gradio_demo/app.py#L39) to torch_dtype = torch.float16, the speed will be greatly improved (1min/img (before) vs. 14s/img (after)). The minimum GPU...

How to use PhotoMaker Style in gradio demo?

https://huggingface.co/spaces/TencentARC/PhotoMaker-Style/tree/main

ValueError: With local_files_only set to None, you must first locally save the tokenizer in the following path: 'openai/clip-vit-large-patch14'.

Try `local_files_only = False`

ValueError: PhotoMaker currently does not support multiple trigger words in a single prompt. Trigger word: img, Prompt: a beautiful girl on Italy street, best quality.

Does the provided prompt have two trigger words?

ValueError: PhotoMaker currently does not support multiple trigger words in a single prompt. Trigger word: img, Prompt: a beautiful girl on Italy street, best quality.

#73 this PR seems to solve the problem. We've merged this PR. You could try our latest version.

ValueError: cannot find context for 'fork'

Please refer to #41

Are There Plans to Offer a Version for SD1.5?

Hi, we don't have this plan yet

cannot import name 'PhotoMakerStableDiffusionXLPipeline'

Now, you could update the environment building through: ```bash conda create --name photomaker python=3.10 pip install -U pip # Install requirements pip install -r requirements.txt # Install photomaker pip install...

cannot import name 'PhotoMakerStableDiffusionXLPipeline'

Could you please provide more details for us?