FLUX.2-dev-bnb-4bit Missing

[ghunkins]

Describe the bug

The diffusers/FLUX.2-dev-bnb-4bit model is missing from Huggingface! Maybe the repo is accidentally set to private?

Huge thank you to the team for the Day 0 support, incredible work!

Reproduction

import diffusers
import torch

hf_path = "diffusers/FLUX.2-dev-bnb-4bit"

pipe = diffusers.Flux2Pipeline.from_pretrained(
    hf_path,
    torch_dtype=torch.bfloat16,
    device_map="cuda",
    local_files_only=True,
)

Logs

except FileNotFoundError:
            # Means we tried to load pipeline with `local_files_only=True` but the files have not been found in local cache.
            # This can happen in two cases:
            # 1. If the user passed `local_files_only=True`                    => we raise the error directly
            # 2. If we forced `local_files_only=True` when `model_info` failed => we raise the initial error
            if model_info_call_error is None:
                # 1. user passed `local_files_only=True`
                raise
            else:
                # 2. we forced `local_files_only=True` when `model_info` failed
>               raise EnvironmentError(
                    f"Cannot load model {pretrained_model_name}: model is not cached locally and an error occurred"
                    " while trying to fetch metadata from the Hub. Please check out the root cause in the stacktrace"
                    " above."
                ) from model_info_call_error
E               OSError: Cannot load model diffusers/FLUX.2-dev-bnb-4bit: model is not cached locally and an error occurred while trying to fetch metadata from the Hub. Please check out the root cause in the stacktrace above.

System Info

N/A

Who can help?

@sayakpaul @yiyixuxu

[sayakpaul]

Public

[ghunkins]

Huge thank you @sayakpaul 🙏