Open msukharam963 opened 5 months ago
Hi~ Have you ever checked the output of the back end? You can check the output in "nohup.out" file when running the back end
D:\Internship\Kintu Designs\StableDiffusionApp\PromptMagician\back-end\server\util.py:46: SyntaxWarning: invalid escape sequence '.' sub_textlist = re.split(',|.|/|;|\'|`|||[|]|<|>|\?|:|"|{|}|\~|!|@|#|\$|%|\^|&|(|)|-|=|\|+|\uff0c|\u3002|\u3001|\uff1b| | |\u3010|\u3011| |\uff01| |\uff08|\uff09', text) [Workflow] device cuda D:\Python\Lib\site-packages\diffusers\utils\outputs.py:63: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. torch.utils._pytree._register_pytree_node( cuda:0 Begin to load model
model_index.json: 0%| | 0.00/541 [00:00<?, ?B/s]
model_index.json: 100%|##########| 541/541 [00:00<?, ?B/s]
D:\Python\Lib\site-packages\huggingface_hub\file_download.py:149: UserWarning: huggingface_hub
cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\Users\msukh.cache\huggingface\hub\models--CompVis--stable-diffusion-v1-4. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the HF_HUB_DISABLE_SYMLINKS_WARNING
environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to see activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
warnings.warn(message)
Fetching 16 files: 0%| | 0/16 [00:00<?, ?it/s] Fetching 16 files: 100%|##########| 16/16 [00:00<00:00, 4015.61it/s]
Loading pipeline components...: 0%| | 0/7 [00:00<?, ?it/s] Loading pipeline components...: 29%|##8 | 2/7 [00:00<00:01, 3.63it/s] Loading pipeline components...: 43%|####2 | 3/7 [00:01<00:02, 1.98it/s] Loading pipeline components...: 57%|#####7 | 4/7 [00:05<00:05, 1.75s/it] Loading pipeline components...: 100%|##########| 7/7 [00:06<00:00, 1.02s/it] Loading pipeline components...: 100%|##########| 7/7 [00:06<00:00, 1.01it/s] Set device Start inference
Running on http://192.168.74.83:5005 Press CTRL+C to quit Guidance scale sample list: [5.0, 5.5, 6.0, 6.5, 7.0, 7.5, 8.0, 8.5, 9.0, 9.5, 10.0, 10.5, 11.0, 11.5, 12.0, 12.5, 13.0, 13.5, 14.0, 14.5, 15.0, 15.5, 16.0, 16.5, 17.0, 17.5, 18.0, 18.5, 19.0, 19.5, 20.0, 20.5, 21.0, 21.5, 22.0, 22.5, 23.0, 23.5, 24.0, 24.5, 25.0, 25.5, 26.0, 26.5, 27.0, 27.5, 28.0, 28.5, 29.0, 29.5, 30.0] negative_prompt is None
0%| | 0/50 [00:00<?, ?it/s]D:\Python\Lib\site-packages\diffusers\models\attention_processor.py:1244: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:263.) hidden_states = F.scaled_dot_product_attention(
2%|2 | 1/50 [00:10<08:37, 10.56s/it] 4%|4 | 2/50 [00:11<04:00, 5.01s/it] 6%|6 | 3/50 [00:20<05:20, 6.81s/it] 8%|8 | 4/50 [00:29<05:51, 7.64s/it] 10%|# | 5/50 [00:38<06:04, 8.11s/it] 12%|#2 | 6/50 [00:47<06:08, 8.38s/it] 14%|#4 | 7/50 [00:56<06:08, 8.56s/it] 16%|#6 | 8/50 [01:05<06:04, 8.69s/it] 18%|#8 | 9/50 [01:14<05:59, 8.76s/it] 20%|## | 10/50 [01:23<05:52, 8.81s/it] 22%|##2 | 11/50 [01:32<05:44, 8.84s/it] 24%|##4 | 12/50 [01:40<05:36, 8.86s/it] 26%|##6 | 13/50 [01:49<05:28, 8.88s/it] 28%|##8 | 14/50 [01:58<05:20, 8.89s/it] 30%|### | 15/50 [02:07<05:11, 8.90s/it] 32%|###2 | 16/50 [02:16<05:02, 8.90s/it] 34%|###4 | 17/50 [02:25<04:53, 8.90s/it] 36%|###6 | 18/50 [02:34<04:44, 8.90s/it] 38%|###8 | 19/50 [02:43<04:35, 8.90s/it] 40%|#### | 20/50 [02:52<04:26, 8.90s/it] 42%|####2 | 21/50 [03:01<04:18, 8.90s/it] 44%|####4 | 22/50 [03:10<04:09, 8.90s/it] 46%|####6 | 23/50 [03:18<04:00, 8.91s/it] 48%|####8 | 24/50 [03:27<03:51, 8.90s/it] 50%|##### | 25/50 [03:36<03:42, 8.90s/it] 52%|#####2 | 26/50 [03:45<03:33, 8.91s/it] 54%|#####4 | 27/50 [03:54<03:24, 8.91s/it] 56%|#####6 | 28/50 [04:03<03:15, 8.90s/it] 58%|#####8 | 29/50 [04:12<03:06, 8.90s/it] 60%|###### | 30/50 [04:21<02:58, 8.90s/it] 62%|######2 | 31/50 [04:30<02:49, 8.90s/it] 64%|######4 | 32/50 [04:39<02:40, 8.90s/it] 66%|######6 | 33/50 [04:47<02:31, 8.90s/it] 68%|######8 | 34/50 [04:56<02:22, 8.90s/it] 70%|####### | 35/50 [05:05<02:13, 8.90s/it] 72%|#######2 | 36/50 [05:14<02:04, 8.90s/it] 74%|#######4 | 37/50 [05:23<01:55, 8.90s/it] 76%|#######6 | 38/50 [05:32<01:46, 8.90s/it] 78%|#######8 | 39/50 [05:41<01:37, 8.90s/it] 80%|######## | 40/50 [05:50<01:28, 8.90s/it] 82%|########2 | 41/50 [05:59<01:20, 8.90s/it] 84%|########4 | 42/50 [06:08<01:11, 8.90s/it] 86%|########6 | 43/50 [06:16<01:02, 8.90s/it] 88%|########8 | 44/50 [06:25<00:53, 8.90s/it] 90%|######### | 45/50 [06:34<00:44, 8.90s/it] 92%|#########2| 46/50 [06:43<00:35, 8.90s/it] 94%|#########3| 47/50 [06:52<00:26, 8.90s/it] 96%|#########6| 48/50 [07:01<00:17, 8.90s/it] 98%|#########8| 49/50 [07:10<00:08, 8.90s/it] 100%|##########| 50/50 [07:19<00:00, 8.90s/it] 100%|##########| 50/50 [07:19<00:00, 8.78s/it] [Infer time: 493.2535514831543] 127.0.0.1 - - [02/Apr/2024 09:51:29] "GET /sd?epo=1&device_id=0&scale_left=5.0&scale_right=30.0&prompt=astronaut+in+ocean&negative_prompt= HTTP/1.1" 200 -
THIS IS THE OUTPUT IN "nohup.out" AND THIS IS IN TERMINAL AFTER "server.py" is executed.
[Workflow] device cuda
Start to load dataset from poloclub/diffusiondb...
D:\Python\Lib\site-packages\datasets\load.py:1454: FutureWarning: The repository for poloclub/diffusiondb contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/poloclub/diffusiondb
You can avoid this message in future by passing the argument trust_remote_code=True
.
Passing trust_remote_code=True
will be mandatory to load this dataset from the next major release of datasets
.
warnings.warn(
Saving the dataset (6/6 shards): 100%|██████████████████████████████████████████████████████████████| 5000/5000 [00:11<00:00, 437.30 examples/s]
Dataset({
features: ['image', 'prompt', 'seed', 'step', 'cfg', 'sampler', 'width', 'height', 'user_name', 'timestamp', 'image_nsfw', 'prompt_nsfw'],
Start to load features from cache...
_getitem
pa_subtable = query_table(self._data, key, indices=self._indices)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Python\Lib\site-packages\datasets\formatting\formatting.py", line 583, in query_table
_check_valid_index_key(key, size)
File "D:\Python\Lib\site-packages\datasets\formatting\formatting.py", line 526, in _check_valid_index_key
raise IndexError(f"Invalid key: {key} is out of bounds for size {size}")
IndexError: Invalid key: 55853 is out of bounds for size 5000
127.0.0.1 - - [02/Apr/2024 09:51:31] "GET /image_overview?prompt=astronaut+in+ocean&negativePrompt=&guidanceScale=5,30&numberOfGeneration=1 HTTP/1.1" 500 -
IndexError: Invalid key: 55853 is out of bounds for size 5000
I guess the error is caused by the mismatch of the dataset. The preprocessed data is based on DiffusionDB 2m_first_100k. If you want to use a different version of the dataset, you need to preprocess it by referring to the workflow.py (Step 3 in README.md)
Thanks for the help. It is working now.
So the code runs perfectly without any issues but while running the front-end the window pops up and while generating the image the image browser just keeps on loading. ANY FIX FOR THAT?