[Admin maintenance] Support new ZeroGPU hardware

Thank you so much for having shared this Space with the community on this demo. We have upgraded the ZeroGPU infra-structure to run on modern blackwell architecture.
For that, we need to upgrade your demo to support that. This PR fixes your demo to work with the new architecture. As this is something we broke on our end, we may merge this PR autonomously. If this breaks unexpectedly or brings unintended consequences, feel free to revert, modify or otherwise. Any issues you can email apolinario@huggingface.co

README.md

@@ -4,7 +4,7 @@ emoji: 😻
 colorFrom: yellow
 colorTo: pink
 sdk: gradio
-sdk_version: 4.19.1
+sdk_version: 5.49.1
 app_file: app.py
 pinned: false
 license: apache-2.0

SDXL/diff_pipe.py

@@ -22,23 +22,37 @@ from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokeniz
 import torchvision
 
 from diffusers.image_processor import VaeImageProcessor
-from diffusers.loaders import FromSingleFileMixin, LoraLoaderMixin, TextualInversionLoaderMixin
+from diffusers.loaders import FromSingleFileMixin, TextualInversionLoaderMixin
+try:
+    from diffusers.loaders import StableDiffusionXLLoraLoaderMixin as LoraLoaderMixin
+except ImportError:
+    from diffusers.loaders import LoraLoaderMixin
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 from diffusers.models.attention_processor import (
     AttnProcessor2_0,
-    LoRAAttnProcessor2_0,
-    LoRAXFormersAttnProcessor,
     XFormersAttnProcessor,
 )
+try:
+    from diffusers.models.attention_processor import LoRAAttnProcessor2_0, LoRAXFormersAttnProcessor
+except ImportError:
+    LoRAAttnProcessor2_0 = AttnProcessor2_0
+    LoRAXFormersAttnProcessor = XFormersAttnProcessor
 from diffusers.schedulers import KarrasDiffusionSchedulers
 from diffusers.utils import (
     is_accelerate_available,
-    is_accelerate_version,
     is_invisible_watermark_available,
     logging,
-    randn_tensor,
     replace_example_docstring,
 )
+try:
+    from diffusers.utils import is_accelerate_version
+except ImportError:
+    def is_accelerate_version(op, ver):
+        return False
+try:
+    from diffusers.utils.torch_utils import randn_tensor
+except ImportError:
+    from diffusers.utils import randn_tensor
 from diffusers.pipelines.pipeline_utils import DiffusionPipeline
 from diffusers.pipelines.stable_diffusion_xl import StableDiffusionXLPipelineOutput
 
@@ -634,23 +648,7 @@ class StableDiffusionXLDiffImg2ImgPipeline(DiffusionPipeline, FromSingleFileMixi
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion_upscale.StableDiffusionUpscalePipeline.upcast_vae
     def upcast_vae(self):
-        dtype = self.vae.dtype
         self.vae.to(dtype=torch.float32)
-        use_torch_2_0_or_xformers = isinstance(
-            self.vae.decoder.mid_block.attentions[0].processor,
-            (
-                AttnProcessor2_0,
-                XFormersAttnProcessor,
-                LoRAXFormersAttnProcessor,
-                LoRAAttnProcessor2_0,
-            ),
-        )
-        # if xformers or torch_2_0 is used attention block does not need
-        # to be in float32 which can save lots of memory
-        if use_torch_2_0_or_xformers:
-            self.vae.post_quant_conv.to(dtype)
-            self.vae.decoder.conv_in.to(dtype)
-            self.vae.decoder.mid_block.to(dtype)
 
     @torch.no_grad()
     @replace_example_docstring(EXAMPLE_DOC_STRING)

app.py

@@ -1,5 +1,5 @@
-import gradio as gr
 import spaces
+import gradio as gr
 import torch
 from torchvision import transforms
 from SDXL.diff_pipe import StableDiffusionXLDiffImg2ImgPipeline

requirements.txt

@@ -1,94 +1,5 @@
-accelerate==0.24.1
-aiofiles==23.2.1
-altair==5.2.0
-annotated-types==0.6.0
-anyio==4.3.0
-attrs==23.2.0
-certifi==2023.11.17
-charset-normalizer==3.3.2
-click==8.1.7
-colorama==0.4.6
-contourpy==1.2.0
-cycler==0.12.1
-diffusers==0.19.3
-exceptiongroup==1.2.0
-fastapi==0.109.2
-ffmpy==0.3.2
-filelock==3.13.1
-fonttools==4.49.0
-fsspec==2023.10.0
-gradio==4.19.1
-gradio_client==0.10.0
-h11==0.14.0
-httpcore==1.0.3
-httpx==0.26.0
-huggingface-hub==0.19.4
-idna==3.4
-importlib-metadata==6.8.0
-importlib-resources==6.1.1
-Jinja2==3.1.2
-jsonschema==4.21.1
-jsonschema-specifications==2023.12.1
-kiwisolver==1.4.5
-markdown-it-py==3.0.0
-MarkupSafe==2.1.3
-matplotlib==3.8.3
-mdurl==0.1.2
-mpmath==1.3.0
-networkx==3.2.1
-numpy==1.26.2
-nvidia-cublas-cu12==12.1.3.1
-nvidia-cuda-cupti-cu12==12.1.105
-nvidia-cuda-nvrtc-cu12==12.1.105
-nvidia-cuda-runtime-cu12==12.1.105
-nvidia-cudnn-cu12==8.9.2.26
-nvidia-cufft-cu12==11.0.2.54
-nvidia-curand-cu12==10.3.2.106
-nvidia-cusolver-cu12==11.4.5.107
-nvidia-cusparse-cu12==12.1.0.106
-nvidia-nccl-cu12==2.18.1
-nvidia-nvjitlink-cu12==12.3.101
-nvidia-nvtx-cu12==12.1.105
-orjson==3.9.14
-packaging==23.2
-pandas==2.2.0
-Pillow==10.1.0
-psutil==5.9.6
-pydantic==2.6.1
-pydantic_core==2.16.2
-pydub==0.25.1
-Pygments==2.17.2
-pyparsing==3.1.1
-python-dateutil==2.8.2
-python-multipart==0.0.9
-pytz==2024.1
-PyYAML==6.0.1
-referencing==0.33.0
-regex==2023.10.3
-requests==2.31.0
-rich==13.7.0
-rpds-py==0.18.0
-ruff==0.2.2
-safetensors==0.4.0
-semantic-version==2.10.0
-sentencepiece==0.1.99
-shellingham==1.5.4
-six==1.16.0
-sniffio==1.3.0
-starlette==0.36.3
-sympy==1.12
-tokenizers==0.15.0
-tomlkit==0.12.0
-toolz==0.12.1
-torch==2.1.1
-torchvision==0.16.1
-tqdm==4.66.1
-transformers==4.35.2
-triton==2.1.0
-typer==0.9.0
-typing_extensions==4.8.0
-tzdata==2024.1
-urllib3==2.1.0
-uvicorn==0.27.1
-websockets==11.0.3
-zipp==3.17.0
+accelerate
+diffusers
+transformers
+torchvision
+sentencepiece