Speed-up by 30%

Dockerfile

@@ -0,0 +1,90 @@
+# Download LFS content while building in order to make this step cacheable
+# #===== LFS =====
+# FROM alpine/git:2.36.2 AS lfs
+# WORKDIR /app
+# COPY --link .lfs.hf.co .
+# RUN --mount=type=secret,id=SPACE_REPOSITORY,mode=0444,required=true \
+#     git init \
+#  && git remote add origin $(cat /run/secrets/SPACE_REPOSITORY) \
+#  && git add --all \
+#  && git config user.email "name@mail.com" \
+#  && git config user.name "Name" \
+#  && git commit -m "lfs" \
+#  && git lfs pull \
+#  && rm -rf .git .gitattributes
+# #===============
+
+FROM nvidia/cuda:11.8.0-runtime-ubuntu18.04
+# BEGIN Static part
+ENV DEBIAN_FRONTEND=noninteractive \
+	TZ=Europe/Paris
+
+RUN apt-get update && apt-get install -y \
+        git \
+        make build-essential libssl-dev zlib1g-dev \
+        libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm \
+        libncursesw5-dev xz-utils tk-dev libxml2-dev libxmlsec1-dev libffi-dev liblzma-dev git-lfs  \
+    	ffmpeg libsm6 libxext6 cmake libgl1-mesa-glx \
+		&& rm -rf /var/lib/apt/lists/* \
+    	&& git lfs install
+
+# User
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+WORKDIR /home/user/app
+
+# Pyenv
+RUN curl https://pyenv.run | bash
+ENV PATH=$HOME/.pyenv/shims:$HOME/.pyenv/bin:$PATH
+
+ARG PIP_VERSION=22.3.1
+ARG PYTHON_VERSION=3.10
+# Python
+RUN pyenv install $PYTHON_VERSION && \
+    pyenv global $PYTHON_VERSION && \
+    pyenv rehash && \
+    pip install --no-cache-dir --upgrade pip==${PIP_VERSION} setuptools wheel && \
+    pip install --no-cache-dir \
+        datasets \
+        "huggingface-hub>=0.12.1" "protobuf<4" "click<8.1"
+
+#^ Waiting for https://github.com/huggingface/huggingface_hub/pull/1345/files to be merge
+
+USER root
+# User Debian packages
+## Security warning : Potential user code executed as root (build time)
+RUN --mount=target=/root/packages.txt,source=packages.txt \
+	apt-get update && \
+    xargs -r -a /root/packages.txt apt-get install -y \
+    && rm -rf /var/lib/apt/lists/*
+    
+USER user
+
+# Pre requirements (e.g. upgrading pip)
+RUN --mount=target=pre-requirements.txt,source=pre-requirements.txt \
+	pip install --no-cache-dir -r pre-requirements.txt
+
+# Python packages
+RUN pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cu117
+RUN --mount=target=requirements.txt,source=requirements.txt \
+	pip install --no-cache-dir -r requirements.txt
+
+ARG SDK=gradio \
+	SDK_VERSION=3.27.0
+RUN pip install --no-cache-dir \
+        ${SDK}==${SDK_VERSION}
+
+# App
+# COPY --link --chown=1000 --from=lfs /app /home/user/app
+COPY --link --chown=1000 ./ /home/user/app
+ENV PYTHONPATH=$HOME/app \
+	PYTHONUNBUFFERED=1 \
+	GRADIO_ALLOW_FLAGGING=never \
+	GRADIO_NUM_PORTS=1 \
+	GRADIO_SERVER_NAME=0.0.0.0 \
+	GRADIO_THEME=huggingface \
+	SYSTEM=spaces
+
+CMD ["python", "app.py"]

README.md

@@ -3,8 +3,7 @@ title: IF
 emoji: 🔥
 colorFrom: pink
 colorTo: red
-sdk: gradio
-sdk_version: 3.27.0
+sdk: docker
 python_version: 3.10.11
 app_file: app.py
 pinned: false

model.py

@@ -59,8 +59,17 @@ class Model:
         if DISABLE_AUTOMATIC_CPU_OFFLOAD:
             self.pipe.to(self.device)
             self.super_res_1_pipe.to(self.device)
+
+            self.pipe.unet.to(memory_format=torch.channels_last)
+            self.pipe.unet = torch.compile(self.pipe.unet, mode="reduce-overhead", fullgraph=True)
+
+            self.super_res_1_pipe.unet.to(memory_format=torch.channels_last)
+            self.super_res_1_pipe.unet = torch.compile(self.super_res_1_pipe.unet, mode="reduce-overhead", fullgraph=True)
+
             if not DISABLE_SD_X4_UPSCALER:
                 self.super_res_2_pipe.to(self.device)
+                self.super_res_2_pipe.unet.to(memory_format=torch.channels_last)
+                self.super_res_2_pipe.unet = torch.compile(self.super_res_2_pipe.unet, mode="reduce-overhead", fullgraph=True)
         else:
             self.pipe.enable_model_cpu_offload()
             self.super_res_1_pipe.enable_model_cpu_offload()

requirements.txt

@@ -1,7 +1,7 @@
 accelerate==0.18.0
 beautifulsoup4==4.12.2
 bitsandbytes==0.38.1
-diffusers==0.16.0
+git+https://github.com/huggingface/diffusers@fix_torch_compile
 ftfy==6.1.1
 gradio==3.27.0
 huggingface_hub==0.14.1
@@ -10,7 +10,5 @@ Pillow==9.5.0
 safetensors==0.3.0
 sentencepiece==0.1.98
 tokenizers==0.13.3
-torch==2.0.0
-torchvision==0.15.1
 tqdm==4.65.0
 transformers==4.28.1