import torch

from optimum.quanto import freeze, qfloat8, quantize

from diffusers import FlowMatchEulerDiscreteScheduler, AutoencoderKL
from diffusers.models.transformers.transformer_flux import FluxTransformer2DModel
from diffusers.pipelines.flux.pipeline_flux import FluxPipeline
from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast

dtype = torch.bfloat16

bfl_repo = "black-forest-labs/FLUX.1-schnell"
revision = "refs/pr/1"
local_path = "FLUX.1-schnell-4bit"

scheduler = FlowMatchEulerDiscreteScheduler.from_pretrained(bfl_repo, subfolder="scheduler", revision=revision)
text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
text_encoder_2 = torch.load(local_path + '/text_encoder_2.pt')
tokenizer_2 = T5TokenizerFast.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype, revision=revision)
vae = AutoencoderKL.from_pretrained(bfl_repo, subfolder="vae", torch_dtype=dtype, revision=revision)
transformer = torch.load(local_path + '/transformer.pt')

pipe = FluxPipeline(
scheduler=scheduler,
text_encoder=text_encoder,
tokenizer=tokenizer,
text_encoder_2=None,
tokenizer_2=tokenizer_2,
vae=vae,
transformer=None,
)
pipe.text_encoder_2 = text_encoder_2
pipe.transformer = transformer

pipe.enable_model_cpu_offload()

pipe.to('cuda')
print('done')
generator = torch.Generator().manual_seed(12345)
pipe(
"a cute apple smiling",
guidance_scale=0.0,
num_inference_steps=4,
max_sequence_length=256,
generator=torch.Generator("cpu").manual_seed(0)
).images[0]

/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning:
The secret HF_TOKEN does not exist in your Colab secrets.
To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.
You will be able to reuse this secret in all of your notebooks.
Please note that authentication is recommended but still optional to access public models or datasets.
warnings.warn(
:19: FutureWarning: You are using torch.load with weights_only=False (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for weights_only will be flipped to True. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via torch.serialization.add_safe_globals. We recommend you start setting weights_only=True for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
text_encoder_2 = torch.load(local_path + '/text_encoder_2.pt')

TypeError Traceback (most recent call last)
in <cell line: 19>()
17 text_encoder = CLIPTextModel.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
18 tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14", torch_dtype=dtype)
---> 19 text_encoder_2 = torch.load(local_path + '/text_encoder_2.pt')
20 tokenizer_2 = T5TokenizerFast.from_pretrained(bfl_repo, subfolder="tokenizer_2", torch_dtype=dtype, revision=revision)
21 vae = AutoencoderKL.from_pretrained(bfl_repo, subfolder="vae", torch_dtype=dtype, revision=revision)

3 frames
/usr/local/lib/python3.10/dist-packages/torch/_utils.py in _rebuild_wrapper_subclass(cls, dtype, size, stride, storage_offset, layout, device, requires_grad)
359 ):
360 device = _get_restore_location(device)
--> 361 return torch.Tensor._make_wrapper_subclass( # type: ignore[attr-defined]
362 cls,
363 size,

TypeError: QBytesTensor must define torch_dispatch