PuLID

PuLID copied to clipboard

how does one transfer glasses style to output image?

1

First off, thank you for creating this model. I been trying out the samples on https://huggingface.co/spaces/yanze/PuLID-FLUX and locally and while the results are really good, I notice glasses are not...

luke-momentusresearch

Hi, My GPU is Tesla P40 24GB VRAM. I am getting the following error: ``` NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs: query : shape=(1, 577, 16, 64) (torch.bfloat16)...

fahadshery

Is 24G VRAM not enough? torch.OutOfMemoryError: CUDA out of memory

4

Hi, I have a 24G VRAM Nvidia Tesla P40 card. I am getting the following error: ``` torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 144.00 MiB. GPU 0 has...

fahadshery

Question about PuLID-FLUX-v0.9.0 model

4

Did this model also train with ID Loss?

cfanyyx

pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema for <class 'starlette.requests.Request'>. Set `arbitrary_types_allowed=True` in the model_config to ignore this error or implement `__get_pydantic_core_schema__` on your type to fully support it.

1

pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema for . Set `arbitrary_types_allowed=True` in the model_config to ignore this error or implement `__get_pydantic_core_schema__` on your type to fully support it. If you got...

lmc710731910

ostris/OpenFLUX.1 is support?

libai-lab

Why when I run app_flux.py, it killed

2

my environment: A100, GRAM 40G, VRAM 72G, it should not be the cache problem

Zhuangvictor0

Downloading shards: 100% 2/2 [00:52

kratos606

Just want to make you aware about a Open Flux (based on Schnell) alternative with apache 2 license: https://huggingface.co/ostris/OpenFLUX.1 Maybe a model can be trained on this flux model?

ThierryDeruyttere

Is there a reason for converting an RGB image to grayscale before feeding it into the model?

2

I'm curious if there is a reason for converting the image to grayscale using the to_gray function on line 192 of the pipeline.py file, "face_features_image = torch.where(bg, white_image, self.to_gray(input))".

kimx3966