ashawkey
commented
2 years ago @frzylucas Hi, have you entered your huggingface access token in the third code block?
Closed frzylucas closed 2 years ago
ashawkey
commented
2 years ago @frzylucas Hi, have you entered your huggingface access token in the third code block?
frzylucas
commented
2 years ago @ashawkey Thank you for the reply! I do remember running that block and successfully logging in when I got that output. I tried running the whole thing again just now just to make sure and am getting a different result, not sure what is causing it because, to my knowledge, I did everything the same way. I'll attach it anyway, maybe it's helpful.
Namespace(H=800, O=True, O2=False, W=800, albedo_iters=1000, angle_front=60, angle_overhead=30, backbone='grid', bg_radius=1.4, bound=1, ckpt='scratch', cuda_ray=True, density_thresh=10, dir_text=True, dt_gamma=0, eval_interval=10, fovy=60, fovy_range=[40, 70], fp16=True, gui=False, guidance='stable-diffusion', h=64, iters=5000, jitter_pose=False, lambda_entropy=0.0001, lambda_opacity=0, lambda_orient=0.01, lambda_smooth=0, light_phi=0, light_theta=60, lr=0.001, max_ray_batch=4096, max_spp=1, max_steps=1024, min_near=0.1, negative='', num_steps=64, radius=3, radius_range=[1.0, 1.5], save_mesh=True, seed=0, suppress_face=False, test=False, text='a DSLR photo of a delicious hamburger', uniform_sphere_rate=0.5, update_extra_interval=16, upsample_steps=64, w=64, workspace='trial')
NeRFNetwork(
(encoder): GridEncoder: input_dim=3 num_levels=16 level_dim=2 resolution=16 -> 2048 per_level_scale=1.3819 params=(903480, 2) gridtype=tiled align_corners=False
(sigma_net): MLP(
(net): ModuleList(
(0): Linear(in_features=32, out_features=64, bias=True)
(1): Linear(in_features=64, out_features=64, bias=True)
(2): Linear(in_features=64, out_features=4, bias=True)
)
)
(encoder_bg): FreqEncoder: input_dim=3 degree=6 output_dim=39
(bg_net): MLP(
(net): ModuleList(
(0): Linear(in_features=39, out_features=64, bias=True)
(1): Linear(in_features=64, out_features=3, bias=True)
)
)
)
[INFO] try to load hugging face access token from the default place, make sure you have run `huggingface-cli login`.
[INFO] loading stable diffusion...
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /usr/local/lib/python3.7/dist-packages/huggingface_hub/utils/_errors.py:213 in │
│ hf_raise_for_status │
│ │
│ 210 │ </Tip> │
│ 211 │ """ │
│ 212 │ try: │
│ ❱ 213 │ │ response.raise_for_status() │
│ 214 │ except HTTPError as e: │
│ 215 │ │ error_code = response.headers.get("X-Error-Code") │
│ 216 │
│ │
│ /usr/local/lib/python3.7/dist-packages/requests/models.py:941 in raise_for_status │
│ │
│ 938 │ │ │ http_error_msg = u'%s Server Error: %s for url: %s' % (self.status_code, rea │
│ 939 │ │ │
│ 940 │ │ if http_error_msg: │
│ ❱ 941 │ │ │ raise HTTPError(http_error_msg, response=self) │
│ 942 │ │
│ 943 │ def close(self): │
│ 944 │ │ """Releases the connection back to the pool. Once this method has been │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
HTTPError: 403 Client Error: Forbidden for url:
https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/vae/diffusion_pytorch_model.bin
The above exception was the direct cause of the following exception:
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /usr/local/lib/python3.7/dist-packages/diffusers/modeling_utils.py:405 in from_pretrained │
│ │
│ 402 │ │ │ │ │ use_auth_token=use_auth_token, │
│ 403 │ │ │ │ │ user_agent=user_agent, │
│ 404 │ │ │ │ │ subfolder=subfolder, │
│ ❱ 405 │ │ │ │ │ revision=revision, │
│ 406 │ │ │ │ ) │
│ 407 │ │ │ │
│ 408 │ │ │ except RepositoryNotFoundError: │
│ │
│ /usr/local/lib/python3.7/dist-packages/huggingface_hub/file_download.py:1057 in hf_hub_download │
│ │
│ 1054 │ │ │ │ │ url=url, │
│ 1055 │ │ │ │ │ use_auth_token=use_auth_token, │
│ 1056 │ │ │ │ │ proxies=proxies, │
│ ❱ 1057 │ │ │ │ │ timeout=etag_timeout, │
│ 1058 │ │ │ │ ) │
│ 1059 │ │ │ except EntryNotFoundError as http_error: │
│ 1060 │ │ │ │ # Cache the non-existence of the file and raise │
│ │
│ /usr/local/lib/python3.7/dist-packages/huggingface_hub/file_download.py:1359 in │
│ get_hf_file_metadata │
│ │
│ 1356 │ │ proxies=proxies, │
│ 1357 │ │ timeout=timeout, │
│ 1358 │ ) │
│ ❱ 1359 │ hf_raise_for_status(r) │
│ 1360 │ │
│ 1361 │ # Return │
│ 1362 │ return HfFileMetadata( │
│ │
│ /usr/local/lib/python3.7/dist-packages/huggingface_hub/utils/_errors.py:254 in │
│ hf_raise_for_status │
│ │
│ 251 │ │ │
│ 252 │ │ # Convert `HTTPError` into a `HfHubHTTPError` to display request information │
│ 253 │ │ # as well (request id and/or server error message) │
│ ❱ 254 │ │ raise HfHubHTTPError(str(HTTPError), response=response) from e │
│ 255 │
│ 256 │
│ 257 def _raise_for_status(response): │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
HfHubHTTPError: <class 'requests.exceptions.HTTPError'> (Request ID: BoMm2nK4Zsy0W5sA5OFjn)
During handling of the above exception, another exception occurred:
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /content/stable-dreamfusion/stable-dreamfusion/main.py:139 in <module> │
│ │
│ 136 │ │ │
│ 137 │ │ if opt.guidance == 'stable-diffusion': │
│ 138 │ │ │ from nerf.sd import StableDiffusion │
│ ❱ 139 │ │ │ guidance = StableDiffusion(device) │
│ 140 │ │ elif opt.guidance == 'clip': │
│ 141 │ │ │ from nerf.clip import CLIP │
│ 142 │ │ │ guidance = CLIP(device) │
│ │
│ /content/stable-dreamfusion/nerf/sd.py:39 in __init__ │
│ │
│ 36 │ │ print(f'[INFO] loading stable diffusion...') │
│ 37 │ │ │
│ 38 │ │ # 1. Load the autoencoder model which will be used to decode the latents into im │
│ ❱ 39 │ │ self.vae = AutoencoderKL.from_pretrained("runwayml/stable-diffusion-v1-5", subfo │
│ 40 │ │ │
│ 41 │ │ # 2. Load the tokenizer and text encoder to tokenize and encode the text. │
│ 42 │ │ self.tokenizer = CLIPTokenizer.from_pretrained("openai/clip-vit-large-patch14") │
│ │
│ /usr/local/lib/python3.7/dist-packages/diffusers/modeling_utils.py:427 in from_pretrained │
│ │
│ 424 │ │ │ │ ) │
│ 425 │ │ │ except HTTPError as err: │
│ 426 │ │ │ │ raise EnvironmentError( │
│ ❱ 427 │ │ │ │ │ "There was a specific connection error when trying to load" │
│ 428 │ │ │ │ │ f" {pretrained_model_name_or_path}:\n{err}" │
│ 429 │ │ │ │ ) │
│ 430 │ │ │ except ValueError: │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
OSError: There was a specific connection error when trying to load runwayml/stable-diffusion-v1-5:
<class 'requests.exceptions.HTTPError'> (Request ID: BoMm2nK4Zsy0W5sA5OFjn)@frzylucas I guess this is the reason: https://news.ycombinator.com/item?id=32556641 You should instead go to check v1.5 though.
frzylucas
commented
2 years ago @ashawkey Yup, was able to run the model smoothly after doing this. Thank you so much!
I'm trying to run some experiments with Stable DreamFusion but I am struggling to get it to work. All seems to be going well until I get to the training section. That's where I keep running into issues. When running this part I get the following output:
pip install accelerate
I've tried accounting for the missing accelerate library by adding
! pip install accelerateto the dependencies step, but that did not help. On an earlier attempt, this seemed to be the only error I was dealing with, but now there is obviously more to it. Granted, I don't really know what I'm doing, so excuse me if the answer to my question is obvious. Thanks in advance.