Zhen Li
Zhen Li
Could you leave me a link to your video and the corresponding mask?
The deadline is approaching. I will check it after that.
OK, thank you for providing a nice solution for us.
Hello, could you please describe it in detail?
It seems that commit 00d961eeba307e1e5b93ad2fac4a48ca7bd58776 from @NEFUJoeyChen has solved this problem.
Hello, what is the size of the image?
Of course, ```python pipe = PhotoMakerStableDiffusionXLPipeline.from_pretrained( base_model_path, # can change to any base model based on SDXL torch_dtype=torch.bfloat16, use_safetensors=True, variant="fp16" ).to(device) ### Load PhotoMaker checkpoint pipe.load_photomaker_adapter( os.path.dirname(photomaker_path), subfolder="", weight_name=os.path.basename(photomaker_path), trigger_word="img"...
Just change the `lora_path` and `adapter_name`
Hello, we have no plans to publish these lists, but we are considering open source our data pipeline.
This is also a solution, but it may not be as effective as uploading multiple photos from multiple angles.