Closed cyril23 closed 11 months ago
I fixed it temporarily by editing the dokerfile present in services/AUTOMATIC111/
FROM alpine/git:2.36.2 as download
COPY clone.sh /clone.sh
RUN . /clone.sh taming-transformers https://github.com/CompVis/taming-transformers.git 24268930bf1dce879235a7fddd0b2355b84d7ea6 \
&& rm -rf data assets **/*.ipynb
RUN . /clone.sh stable-diffusion-stability-ai https://github.com/Stability-AI/stablediffusion.git 47b6b607fdd31875c9279cd2f4f16b92e4ea958e \
&& rm -rf assets data/**/*.png data/**/*.jpg data/**/*.gif
RUN . /clone.sh CodeFormer https://github.com/sczhou/CodeFormer.git c5b4593074ba6214284d6acd5f1719b6c5d739af \
&& rm -rf assets inputs
RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c9f7a5b4813144b2fb9
RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git c9fe758757e022f05ca5a53fa8fac28889e4f1cf
RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2486589f24165c8e3b303f84e9dbbea318df83e8
RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-models 45c443b316737a4ab6e40413d7794a7f5657c19f
FROM alpine:3.17 as xformers
RUN apk add --no-cache aria2
RUN aria2c -x 5 --dir / --out wheel.whl 'https://github.com/AbdBarho/stable-diffusion-webui-docker/releases/download/6.0.0/xformers-0.0.21.dev544-cp310-cp310-manylinux2014_x86_64-pytorch201.whl'
FROM python:3.10.13-slim
ENV DEBIAN_FRONTEND=noninteractive PIP_PREFER_BINARY=1
RUN --mount=type=cache,target=/var/cache/apt \
apt-get update && \
# we need those
apt-get install -y fonts-dejavu-core rsync git jq moreutils aria2 \
# extensions needs those
ffmpeg libglfw3-dev libgles2-mesa-dev pkg-config libcairo2 libcairo2-dev build-essential
RUN --mount=type=cache,target=/cache --mount=type=cache,target=/root/.cache/pip \
aria2c -x 5 --dir /cache --out torch-2.0.1-cp310-cp310-linux_x86_64.whl -c \
https://download.pytorch.org/whl/cu118/torch-2.0.1%2Bcu118-cp310-cp310-linux_x86_64.whl && \
pip install /cache/torch-2.0.1-cp310-cp310-linux_x86_64.whl torchvision --index-url https://download.pytorch.org/whl/cu118
COPY requirements_versions.txt /requirements_versions.txt
RUN --mount=type=cache,target=/root/.cache/pip \
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git && \
cd stable-diffusion-webui && \
git reset --hard 20ae71faa8ef035c31aa3a410b707d792c8203a3 && \
pip install -r /requirements_versions.txt
RUN --mount=type=cache,target=/root/.cache/pip \
--mount=type=bind,from=xformers,source=/wheel.whl,target=/xformers-0.0.21.dev544-cp310-cp310-manylinux2014_x86_64.whl \
pip install /xformers-0.0.21.dev544-cp310-cp310-manylinux2014_x86_64.whl
ENV ROOT=/stable-diffusion-webui
COPY --from=download /repositories/ ${ROOT}/repositories/
RUN mkdir ${ROOT}/interrogate && cp ${ROOT}/repositories/clip-interrogator/data/* ${ROOT}/interrogate
RUN --mount=type=cache,target=/root/.cache/pip \
pip install -r ${ROOT}/repositories/CodeFormer/requirements.txt
RUN --mount=type=cache,target=/root/.cache/pip \
pip install pyngrok \
git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379 \
git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1 \
git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b
# Note: don't update the sha of previous versions because the install will take forever
# instead, update the repo state in a later step
# TODO: either remove if fixed in A1111 (unlikely) or move to the top with other apt stuff
RUN apt-get -y install libgoogle-perftools-dev && apt-get clean
ENV LD_PRELOAD=libtcmalloc.so
ARG SHA=68f336bd994bed5442ad95bad6b6ad5564a5409a
RUN --mount=type=cache,target=/root/.cache/pip \
cd stable-diffusion-webui && \
git fetch && \
git reset --hard ${SHA} && \
pip install -r requirements_versions.txt \
pip install -U pip && \
pip install -U httpcore && \
pip3 install httpx==0.24.1
COPY . /docker
RUN \
python3 /docker/info.py ${ROOT}/modules/ui.py && \
mv ${ROOT}/style.css ${ROOT}/user.css && \
# one of the ugliest hacks I ever wrote \
sed -i 's/in_app_dir = .*/in_app_dir = True/g' /usr/local/lib/python3.10/site-packages/gradio/routes.py && \
git config --global --add safe.directory '*'
WORKDIR ${ROOT}
ENV NVIDIA_VISIBLE_DEVICES=all
ENV CLI_ARGS=""
EXPOSE 7860
ENTRYPOINT ["/docker/entrypoint.sh"]
CMD python -u webui.py --listen --port 7860 ${CLI_ARGS}
and by adding a file called requirements_versions.txt in that same folder. here's the content of the file
GitPython==3.1.32
Pillow==9.5.0
accelerate==0.21.0
basicsr==1.4.2
blendmodes==2022
clean-fid==0.1.35
einops==0.4.1
fastapi==0.94.0
gfpgan==1.3.8
gradio==3.41.2
httpx==0.24.1
httpcore==0.15
inflection==0.5.1
jsonmerge==1.8.0
kornia==0.6.7
lark==1.1.2
numpy==1.23.5
omegaconf==2.2.3
open-clip-torch==2.20.0
piexif==1.1.3
psutil==5.9.5
pytorch_lightning==1.9.4
realesrgan==0.3.0
resize-right==0.0.2
safetensors==0.3.1
scikit-image==0.21.0
timm==0.9.2
tomesd==0.1.3
torch
torchdiffeq==0.2.3
torchsde==0.2.5
transformers==4.30.2
httpx==0.24.1
this applies the fix you mentioned in your post :)
thanks for the quick reply!, edit: because of your custom Dockerfile
and the requirements_versions.txt
you provided, I was able to open the GUI now, but get an error if I do any txt2img or img2img request on the v1-5-pruned-emaonly.ckpt
(prompt: happy guy
, the rest are stock settings)
webui-docker-auto-1 | Calculating sha256 for /stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt: cc6cb27103417325ff94f52b7a5d2dde45a7515b25c255d8e396c90014281516
webui-docker-auto-1 | Loading weights [cc6cb27103] from /stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt
webui-docker-auto-1 | Creating model from config: /stable-diffusion-webui/configs/v1-inference.yaml
webui-docker-auto-1 | LatentDiffusion: Running in eps-prediction mode
webui-docker-auto-1 | DiffusionWrapper has 859.52 M params.
webui-docker-auto-1 | Applying attention optimization: xformers... done.
webui-docker-auto-1 | Model loaded in 1.7s (create model: 0.5s, apply weights to model: 0.7s, apply half(): 0.3s, calculate empty prompt: 0.1s).
0% 0/16 [00:00<?, ?it/s]
webui-docker-auto-1 | *** Error completing request
webui-docker-auto-1 | *** Arguments: ('task(ue0649ifuscybol)', 'happy guy', '', [], 16, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 0, '', '', [], <gradio.routes.Request object at 0x7f67fe8800a0>, 0, 'from modules.processing import process_images\n\np.width = 768\np.height = 768\np.batch_size = 2\np.steps = 10\n\nreturn process_images(p)', 2, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0) {}
webui-docker-auto-1 | Traceback (most recent call last):
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/call_queue.py", line 58, in f
webui-docker-auto-1 | res = list(func(*args, **kwargs))
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/call_queue.py", line 37, in f
webui-docker-auto-1 | res = func(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/txt2img.py", line 62, in txt2img
webui-docker-auto-1 | processed = processing.process_images(p)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/processing.py", line 677, in process_images
webui-docker-auto-1 | res = process_images_inner(p)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/processing.py", line 794, in process_images_inner
webui-docker-auto-1 | samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/processing.py", line 1054, in sample
webui-docker-auto-1 | samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 464, in sample
webui-docker-auto-1 | samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 303, in launch_sampling
webui-docker-auto-1 | return func()
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 464, in <lambda>
webui-docker-auto-1 | samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
webui-docker-auto-1 | return func(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/sampling.py", line 145, in sample_euler_ancestral
webui-docker-auto-1 | denoised = model(x, sigmas[i] * s_in, **extra_args)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_samplers_kdiffusion.py", line 189, in forward
webui-docker-auto-1 | x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(subscript_cond(cond_in, a, b), image_cond_in[a:b]))
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 112, in forward
webui-docker-auto-1 | eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/k-diffusion/k_diffusion/external.py", line 138, in get_eps
webui-docker-auto-1 | return self.inner_model.apply_model(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_hijack_utils.py", line 17, in <lambda>
webui-docker-auto-1 | setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_hijack_utils.py", line 28, in __call__
webui-docker-auto-1 | return self.__orig_func(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 858, in apply_model
webui-docker-auto-1 | x_recon = self.model(x_noisy, t, **cond)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1568, in _call_impl
webui-docker-auto-1 | result = forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 1329, in forward
webui-docker-auto-1 | out = self.diffusion_model(x, t, context=cc)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_unet.py", line 91, in UNetModel_forward
webui-docker-auto-1 | return ldm.modules.diffusionmodules.openaimodel.copy_of_UNetModel_forward_for_webui(self, x, timesteps, context, *args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py", line 776, in forward
webui-docker-auto-1 | h = module(h, emb, context)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py", line 84, in forward
webui-docker-auto-1 | x = layer(x, context)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/attention.py", line 324, in forward
webui-docker-auto-1 | x = block(x, context=context[i])
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/attention.py", line 259, in forward
webui-docker-auto-1 | return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/util.py", line 114, in checkpoint
webui-docker-auto-1 | return CheckpointFunction.apply(func, len(inputs), *args)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/autograd/function.py", line 539, in apply
webui-docker-auto-1 | return super().apply(*args, **kwargs) # type: ignore[misc]
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/util.py", line 129, in forward
webui-docker-auto-1 | output_tensors = ctx.run_function(*ctx.input_tensors)
webui-docker-auto-1 | File "/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/modules/attention.py", line 262, in _forward
webui-docker-auto-1 | x = self.attn1(self.norm1(x), context=context if self.disable_self_attn else None) + x
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl
webui-docker-auto-1 | return self._call_impl(*args, **kwargs)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl
webui-docker-auto-1 | return forward_call(*args, **kwargs)
webui-docker-auto-1 | File "/stable-diffusion-webui/modules/sd_hijack_optimizations.py", line 489, in xformers_attention_forward
webui-docker-auto-1 | out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=get_xformers_flash_attention_op(q, k, v))
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 192, in memory_efficient_attention
webui-docker-auto-1 | return _memory_efficient_attention(
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 290, in _memory_efficient_attention
webui-docker-auto-1 | return _memory_efficient_attention_forward(
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/xformers/ops/fmha/__init__.py", line 306, in _memory_efficient_attention_forward
webui-docker-auto-1 | op = _dispatch_fw(inp)
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 94, in _dispatch_fw
webui-docker-auto-1 | return _run_priority_list(
webui-docker-auto-1 | File "/usr/local/lib/python3.10/site-packages/xformers/ops/fmha/dispatch.py", line 69, in _run_priority_list
webui-docker-auto-1 | raise NotImplementedError(msg)
webui-docker-auto-1 | NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:
webui-docker-auto-1 | query : shape=(1, 4096, 8, 40) (torch.float16)
webui-docker-auto-1 | key : shape=(1, 4096, 8, 40) (torch.float16)
webui-docker-auto-1 | value : shape=(1, 4096, 8, 40) (torch.float16)
webui-docker-auto-1 | attn_bias : <class 'NoneType'>
webui-docker-auto-1 | p : 0.0
webui-docker-auto-1 | `flshattF` is not supported because:
webui-docker-auto-1 | xFormers wasn't build with CUDA support
webui-docker-auto-1 | Operator wasn't built - see `python -m xformers.info` for more info
webui-docker-auto-1 | `tritonflashattF` is not supported because:
webui-docker-auto-1 | xFormers wasn't build with CUDA support
webui-docker-auto-1 | requires A100 GPU
webui-docker-auto-1 | Only work on pre-MLIR triton for now
webui-docker-auto-1 | `cutlassF` is not supported because:
webui-docker-auto-1 | xFormers wasn't build with CUDA support
webui-docker-auto-1 | Operator wasn't built - see `python -m xformers.info` for more info
webui-docker-auto-1 | `smallkF` is not supported because:
webui-docker-auto-1 | xFormers wasn't build with CUDA support
webui-docker-auto-1 | dtype=torch.float16 (supported: {torch.float32})
webui-docker-auto-1 | max(query.shape[-1] != value.shape[-1]) > 32
webui-docker-auto-1 | Operator wasn't built - see `python -m xformers.info` for more info
webui-docker-auto-1 | unsupported embed per head: 40
webui-docker-auto-1 |
webui-docker-auto-1 | ---
During startup I see a warning too:
~/stable-diffusion-webui-docker$ docker compose --profile auto up --build
[+] Building 1.0s (34/34) FINISHED docker:default
=> [auto internal] load build definition from Dockerfile 0.0s
=> => transferring dockerfile: 4.43kB 0.0s
=> [auto internal] load .dockerignore 0.0s
=> => transferring context: 2B 0.0s
=> [auto internal] load metadata for docker.io/library/alpine:3.17 0.9s
=> [auto internal] load metadata for docker.io/library/python:3.10.13-slim 0.9s
=> [auto internal] load metadata for docker.io/alpine/git:2.36.2 0.9s
=> [auto download 1/9] FROM docker.io/alpine/git:2.36.2@sha256:ec491c893597b68c92b88023827faa771772cfd5e106b76c713fa5e1c75dea84 0.0s
=> [auto internal] load build context 0.0s
=> => transferring context: 194B 0.0s
=> [auto stage-2 1/15] FROM docker.io/library/python:3.10.13-slim@sha256:3c9182c6498d7de6044be04fb1785ba3a04f953d515d45e5007e8be1c15fdd34 0.0s
=> [auto xformers 1/3] FROM docker.io/library/alpine:3.17@sha256:f71a5f071694a785e064f05fed657bf8277f1b2113a8ed70c90ad486d6ee54dc 0.0s
=> CACHED [auto stage-2 2/15] RUN --mount=type=cache,target=/var/cache/apt apt-get update && apt-get install -y fonts-dejavu-core rsync gi 0.0s
=> CACHED [auto stage-2 3/15] RUN --mount=type=cache,target=/cache --mount=type=cache,target=/root/.cache/pip aria2c -x 5 --dir /cache --out 0.0s
=> CACHED [auto stage-2 4/15] COPY requirements_versions.txt /requirements_versions.txt 0.0s
=> CACHED [auto stage-2 5/15] RUN --mount=type=cache,target=/root/.cache/pip git clone https://github.com/AUTOMATIC1111/stable-diffusion-web 0.0s
=> CACHED [auto xformers 2/3] RUN apk add --no-cache aria2 0.0s
=> CACHED [auto xformers 3/3] RUN aria2c -x 5 --dir / --out wheel.whl 'https://github.com/AbdBarho/stable-diffusion-webui-docker/releases/downl 0.0s
=> CACHED [auto stage-2 6/15] RUN --mount=type=cache,target=/root/.cache/pip --mount=type=bind,from=xformers,source=/wheel.whl,target=/xfor 0.0s
=> CACHED [auto download 2/9] COPY clone.sh /clone.sh 0.0s
=> CACHED [auto download 3/9] RUN . /clone.sh taming-transformers https://github.com/CompVis/taming-transformers.git 24268930bf1dce879235a7fddd 0.0s
=> CACHED [auto download 4/9] RUN . /clone.sh stable-diffusion-stability-ai https://github.com/Stability-AI/stablediffusion.git 47b6b607fdd3187 0.0s
=> CACHED [auto download 5/9] RUN . /clone.sh CodeFormer https://github.com/sczhou/CodeFormer.git c5b4593074ba6214284d6acd5f1719b6c5d739af && 0.0s
=> CACHED [auto download 6/9] RUN . /clone.sh BLIP https://github.com/salesforce/BLIP.git 48211a1594f1321b00f14c9f7a5b4813144b2fb9 0.0s
=> CACHED [auto download 7/9] RUN . /clone.sh k-diffusion https://github.com/crowsonkb/k-diffusion.git c9fe758757e022f05ca5a53fa8fac28889e4f1cf 0.0s
=> CACHED [auto download 8/9] RUN . /clone.sh clip-interrogator https://github.com/pharmapsychotic/clip-interrogator 2486589f24165c8e3b303f84e9 0.0s
=> CACHED [auto download 9/9] RUN . /clone.sh generative-models https://github.com/Stability-AI/generative-models 45c443b316737a4ab6e40413d7794 0.0s
=> CACHED [auto stage-2 7/15] COPY --from=download /repositories/ /stable-diffusion-webui/repositories/ 0.0s
=> CACHED [auto stage-2 8/15] RUN mkdir /stable-diffusion-webui/interrogate && cp /stable-diffusion-webui/repositories/clip-interrogator/data/ 0.0s
=> CACHED [auto stage-2 9/15] RUN --mount=type=cache,target=/root/.cache/pip pip install -r /stable-diffusion-webui/repositories/CodeFormer/ 0.0s
=> CACHED [auto stage-2 10/15] RUN --mount=type=cache,target=/root/.cache/pip pip install pyngrok git+https://github.com/TencentARC/GFPGAN. 0.0s
=> CACHED [auto stage-2 11/15] RUN apt-get -y install libgoogle-perftools-dev && apt-get clean 0.0s
=> CACHED [auto stage-2 12/15] RUN --mount=type=cache,target=/root/.cache/pip cd stable-diffusion-webui && git fetch && git reset --hard 0.0s
=> CACHED [auto stage-2 13/15] COPY . /docker 0.0s
=> CACHED [auto stage-2 14/15] RUN python3 /docker/info.py /stable-diffusion-webui/modules/ui.py && mv /stable-diffusion-webui/style.css /s 0.0s
=> CACHED [auto stage-2 15/15] WORKDIR /stable-diffusion-webui 0.0s
=> [auto] exporting to image 0.0s
=> => exporting layers 0.0s
=> => writing image sha256:466f66db6474ac74079e4ab400e19cf6a7a3ced30c9200047ddde59f42f440f1 0.0s
=> => naming to docker.io/library/sd-auto:67 0.0s
[+] Running 1/0
✔ Container webui-docker-auto-1 Created 0.0s
Attaching to webui-docker-auto-1
webui-docker-auto-1 | Mounted .cache
webui-docker-auto-1 | Mounted config_states
webui-docker-auto-1 | Mounted .cache
webui-docker-auto-1 | Mounted embeddings
webui-docker-auto-1 | Mounted config.json
webui-docker-auto-1 | Mounted models
webui-docker-auto-1 | Mounted styles.csv
webui-docker-auto-1 | Mounted ui-config.json
webui-docker-auto-1 | Mounted extensions
webui-docker-auto-1 | Installing extension dependencies (if any)
webui-docker-auto-1 | WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
webui-docker-auto-1 | PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.1.0+cu121)
webui-docker-auto-1 | Python 3.10.11 (you have 3.10.13)
webui-docker-auto-1 | Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)
webui-docker-auto-1 | Memory-efficient attention, SwiGLU, sparse and more won't be available.
webui-docker-auto-1 | Set XFORMERS_MORE_DETAILS=1 for more details
webui-docker-auto-1 | Loading weights [cc6cb27103] from /stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.ckpt
webui-docker-auto-1 | Running on local URL: http://0.0.0.0:7860
webui-docker-auto-1 |
webui-docker-auto-1 | To create a public link, set `share=True` in `launch()`.
webui-docker-auto-1 | Startup time: 13.2s (import torch: 6.3s, import gradio: 1.2s, setup paths: 2.9s, other imports: 1.2s, setup codeformer: 0.1s, load scripts: 0.5s, create ui: 0.7s, gradio launch: 0.1s, add APIs: 0.1s).
webui-docker-auto-1 | Creating model from config: /stable-diffusion-webui/configs/v1-inference.yaml
webui-docker-auto-1 | LatentDiffusion: Running in eps-prediction mode
webui-docker-auto-1 | DiffusionWrapper has 859.52 M params.
webui-docker-auto-1 | Applying attention optimization: xformers... done.
webui-docker-auto-1 | Model loaded in 11.5s (load weights from disk: 9.6s, create model: 0.5s, apply weights to model: 0.6s, apply half(): 0.2s, calculate empty prompt: 0.5s).
(edit: removed duplicate citations)
There are some issues about this:
Maybe my CUDA 121 (or CUDA Version: 12.2
according to nvidia-smi) or my PyTorch version is too new?
According to https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers I can try to run SD without xformers as it only seems to be a performance enhancement.
I've disabled xformers by editing docker-compose.yml
and removing --xformers
from the line here https://github.com/AbdBarho/stable-diffusion-webui-docker/blob/6a34739135eb112667f00943c1fac98ab294716a/docker-compose.yml#L34
Now text2img, img2img etc. fully work! Not sure if I should open a new issue for this, since I'm running your customized Dockerfile
I believe this issue has been fixed. We only needs to change here:
https://github.com/AbdBarho/stable-diffusion-webui-docker/blob/6a34739135eb112667f00943c1fac98ab294716a/services/AUTOMATIC1111/Dockerfile#L44
to the latest commit of AUTOMATIC111 4afaaf8a020c1df457bcf7250cb1c7f609699fa7
which add the httpx==0.24.1
in the requirement file: #13839
Thanks all, confirming that updating services/AUTOMATIC1111/Dockerfile
to use that commit (4afaaf8
) with the httpx
pin worked for me.
Thanks! I can confirm it, too. It works like this, on a fresh Amazon EC2 instance (edit: still using an Amazon g5.xlarge instance (NVIDIA A10G Tensor-Core-GPU) with an EC2 Deep Learning Base GPU AMI (Ubuntu 20.04) 20231026 (ami-0d134e01570c1e7b4) image):
git clone https://github.com/AbdBarho/stable-diffusion-webui-docker.git && \
cd stable-diffusion-webui-docker/ && \
sed -i 's/5ef669de080814067961f28357256e8fe27544f4/4afaaf8a020c1df457bcf7250cb1c7f609699fa7/g' services/AUTOMATIC1111/Dockerfile && \
docker compose --profile download up --build
# Amazon EC2 only: need to login to docker to avoid error "failed to authorize: failed to fetch anonymous token"
aws configure
# enter access token credentials, see AWS iam
aws ecr get-login-password --region {your region, e.g. eu-central-1} | docker login --username AWS --password-stdin {aws domain of that region, e.g. 763104351884.dkr.ecr.eu-central-1.amazonaws.com}
docker compose --profile auto up --build
I left a comment on the related PR here https://github.com/AbdBarho/stable-diffusion-webui-docker/pull/609#discussion_r1390246340
I think I can close this here now
Thank you for solving this, and sorry for coming so late to this.
I did some updates in #610. Would be great if anyone could test the new version and re-open this issue if the problem remains.
Thanks a lot @AbdBarho, testing now :)
EDIT: confirming the PR build works well for me. Also, good catch on other things like the leftover sygil
references :rocket:
I updated to the latest version, but the same error still occurs."
Has this issue been opened before?
Describe the bug
I've tried to run the auto (AUTOMATIC1111) UI, following the wiki, and get the following error:
Which UI
auto
Hardware / Software
master
andgit checkout tags/8.1.0
Steps to Reproduce
Additional context
Using a Amazon g5.xlarge instance (NVIDIA A10G Tensor-Core-GPU) with an EC2 Deep Learning Base GPU AMI (Ubuntu 20.04) 20231026 (ami-0d134e01570c1e7b4) image.
By the way, trying the
invoke
UI doesn't work either for me, see https://github.com/AbdBarho/stable-diffusion-webui-docker/issues/595#issuecomment-1793470108Side note
On a completely different setup on a Google g2-standard-4 machine (Nvidia L4) with a "Deep Learning VM with CUDA 12.1 M112" (c0-deeplearning-common-cu121-v20230925-debian-11-py310) image, I've successfully started AUTOMATIC without Docker but using https://github.com/AUTOMATIC1111/stable-diffusion-webui directly via
but sometimes on
python3 launch.py
I see the same errorgot an unexpected keyword argument 'socket_options'
, but according to the following issues on the https://github.com/AUTOMATIC1111/stable-diffusion-webui/ repo:I could fix it as follows:
But in this https://github.com/AbdBarho/stable-diffusion-webui-docker repo I don't know how to apply this.