Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

About pix2pix access huggingface URL #112

Open
yoker5262 opened this issue Aug 17, 2023 · 0 comments
Open

About pix2pix access huggingface URL #112

yoker5262 opened this issue Aug 17, 2023 · 0 comments

Comments

@yoker5262
Copy link

my code:
image = Image.fromarray(image)
pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timbrooks/instruct-pix2pix",
torch_dtype=torch.float16,
safety_checker=None)
pipe.to("cuda")
pipe.scheduler = DDIMScheduler.from_pretrained("CompVis/stable-diffusion-v1-4", subfolder="scheduler")
num_inference_steps = 200
image_guidance_scale = 2.1
guidance_scale = 8.35
images = pipe(text_prompt, image=image, num_inference_steps=num_inference_steps, image_guidance_scale=image_guidance_scale,guidance_scale=guidance_scale).images[0]
images = np.array(images)
numbers = datetime.now().strftime("%Y%m%d%H%M%S")
cv2.imwrite(f"outputs/{imagename.split('.')[0]+str({image_guidance_scale})+':'+str({guidance_scale})+':'+str({num_inference_steps}) + ':'+ numbers + ':'+ text_prompt}.png", images)

error message:
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /home/yoker/codes/image-synthesis/imageSyn-algorthmsManage/algorithms_manage │
│ /algorithm_pool/model_code/instruct-nerf2nerf/main.py:61 in │
│ │
│ 58 │ # ) │
│ 59 │ │
│ 60 │ image = Image.fromarray(image) │
│ ❱ 61 │ pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("timb │
│ 62 │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ torch │
│ 63 │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ safet │
│ 64 │ pipe.to("cuda") │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/diffusers/pipel │
│ ines/pipeline_utils.py:910 in from_pretrained │
│ │
│ 907 │ │ if not os.path.isdir(pretrained_model_name_or_path): │
│ 908 │ │ │ print(pretrained_model_name_or_path) │
│ 909 │ │ │ print(cache_dir) │
│ ❱ 910 │ │ │ cached_folder = cls.download( │
│ 911 │ │ │ │ pretrained_model_name_or_path, │
│ 912 │ │ │ │ cache_dir=cache_dir, │
│ 913 │ │ │ │ resume_download=resume_download, │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/diffusers/pipel │
│ ines/pipeline_utils.py:1221 in download │
│ │
│ 1218 │ │ │
│ 1219 │ │ if not local_files_only: │
│ 1220 │ │ │ try: │
│ ❱ 1221 │ │ │ │ info = model_info( │
│ 1222 │ │ │ │ │ pretrained_model_name, │
│ 1223 │ │ │ │ │ use_auth_token=use_auth_token, │
│ 1224 │ │ │ │ │ revision=revision, │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/huggingface_hub │
│ /utils/_validators.py:118 in _inner_fn │
│ │
│ 115 │ │ if check_use_auth_token: │
│ 116 │ │ │ kwargs = smoothly_deprecate_use_auth_token(fn_name=fn.__na │
│ 117 │ │ │
│ ❱ 118 │ │ return fn(*args, **kwargs) │
│ 119 │ │
│ 120 │ return _inner_fn # type: ignore │
│ 121 │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/huggingface_hub │
│ /hf_api.py:1675 in model_info │
│ │
│ 1672 │ │ │ params["securityStatus"] = True │
│ 1673 │ │ if files_metadata: │
│ 1674 │ │ │ params["blobs"] = True │
│ ❱ 1675 │ │ r = get_session().get(path, headers=headers, timeout=timeout, │
│ 1676 │ │ hf_raise_for_status(r) │
│ 1677 │ │ d = r.json() │
│ 1678 │ │ return ModelInfo(**d) │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/requests/sessio │
│ ns.py:602 in get │
│ │
│ 599 │ │ """ │
│ 600 │ │ │
│ 601 │ │ kwargs.setdefault("allow_redirects", True) │
│ ❱ 602 │ │ return self.request("GET", url, **kwargs) │
│ 603 │ │
│ 604 │ def options(self, url, **kwargs): │
│ 605 │ │ r"""Sends a OPTIONS request. Returns :class:Response object. │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/requests/sessio │
│ ns.py:589 in request │
│ │
│ 586 │ │ │ "allow_redirects": allow_redirects, │
│ 587 │ │ } │
│ 588 │ │ send_kwargs.update(settings) │
│ ❱ 589 │ │ resp = self.send(prep, **send_kwargs) │
│ 590 │ │ │
│ 591 │ │ return resp │
│ 592 │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/requests/sessio │
│ ns.py:703 in send │
│ │
│ 700 │ │ start = preferred_clock() │
│ 701 │ │ │
│ 702 │ │ # Send the request │
│ ❱ 703 │ │ r = adapter.send(request, **kwargs) │
│ 704 │ │ │
│ 705 │ │ # Total elapsed time of the request (approximately) │
│ 706 │ │ elapsed = preferred_clock() - start │
│ │
│ /home/yoker/miniconda3/envs/alg/lib/python3.10/site-packages/requests/adapte │
│ rs.py:501 in send │
│ │
│ 498 │ │ │ ) │
│ 499 │ │ │
│ 500 │ │ except (ProtocolError, OSError) as err: │
│ ❱ 501 │ │ │ raise ConnectionError(err, request=request) │
│ 502 │ │ │
│ 503 │ │ except MaxRetryError as e: │
│ 504 │ │ │ if isinstance(e.reason, ConnectTimeoutError): │
╰──────────────────────────────────────────────────────────────────────────────╯
ConnectionError: (ProtocolError('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer')), '(Request ID:
21a01d15-c1aa-4256-9a82-99b35f5dbb52)')

question:

Why does it always connect to the network to access huggingface when executing pix2pix? Shouldn't the required files be downloaded to the local cache the first time it is executed? Is it a necessary step if huggingface is accessed for every execution? This causes my program to report errors frequently, because my network access to huggingface is very difficult!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant