Comments (19)
Gitterman69
commented on August 29, 2024
bump - same
from rave.
ozgurkara99
commented on August 29, 2024
Thank you for your interest and opening issue, we are working on the demo to be able to run in Windows, and the instructions for Windows will be available soon. We would suggest you to use Linux OS.
from rave.
ozgurkara99
commented on August 29, 2024
Could you please give more details? At which step have you encountered that error? It is when you click 'Run' button? In the recent commit, I have updated the paths such that it should become compatible with Windows. Thanks
from rave.
SoftologyPro
commented on August 29, 2024
New error now. I use the settings shown in the screenshot below. When I click Run All I get these errors.
Do I need to manually download some extra models?
C:\Users\Jason\AppData\Local\Temp\gradio\8aad7b5c09060a0858874df8fd3cce2a390d68b2\wolf.mp4
Frame count: 4
vae\diffusion_pytorch_model.safetensors not found
Traceback (most recent call last):
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 456, in call_prediction
output = await route_utils.call_process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
output = await app.get_blocks().process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1522, in process_api
result = await self.call_function(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1144, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
result = context.run(func, *args)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\utils.py", line 674, in wrapper
response = f(*args, **kwargs)
File "D:\Tests\RAVE\webui.py", line 132, in run
CN.init_models(input_ns.hf_cn_path, input_ns.hf_path, input_ns.preprocess_name, input_ns.model_id)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 49, in init_models
pipe = self.__init_pipe(hf_cn_path, hf_path)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 43, in __init_pipe
pipe.enable_xformers_memory_efficient_attention()
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1442, in enable_xformers_memory_efficient_attention
self.set_use_memory_efficient_attention_xformers(True, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1468, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1458, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 227, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 220, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 227, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 220, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\attention_processor.py", line 192, in set_use_memory_efficient_attention_xformers
raise ModuleNotFoundError(
ModuleNotFoundError: Refer to https://github.com/facebookresearch/xformers for more information on how to install xformers
Traceback (most recent call last):
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 456, in call_prediction
output = await route_utils.call_process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
output = await app.get_blocks().process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1522, in process_api
result = await self.call_function(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1144, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
result = context.run(func, *args)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\utils.py", line 674, in wrapper
response = f(*args, **kwargs)
File "D:\Tests\RAVE\webui.py", line 132, in run
CN.init_models(input_ns.hf_cn_path, input_ns.hf_path, input_ns.preprocess_name, input_ns.model_id)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 49, in init_models
pipe = self.__init_pipe(hf_cn_path, hf_path)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 43, in __init_pipe
pipe.enable_xformers_memory_efficient_attention()
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1442, in enable_xformers_memory_efficient_attention
self.set_use_memory_efficient_attention_xformers(True, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1468, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1458, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 227, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 220, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 227, in set_use_memory_efficient_attention_xformers
fn_recursive_set_mem_eff(module)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 223, in fn_recursive_set_mem_eff
fn_recursive_set_mem_eff(child)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\modeling_utils.py", line 220, in fn_recursive_set_mem_eff
module.set_use_memory_efficient_attention_xformers(valid, attention_op)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\diffusers\models\attention_processor.py", line 192, in set_use_memory_efficient_attention_xformers
raise ModuleNotFoundError(
ModuleNotFoundError: Refer to https://github.com/facebookresearch/xformers for more information on how to install xformers
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 501, in process_events
response = await self.call_prediction(awake_events, batch)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 465, in call_prediction
raise Exception(str(error) if show_error else None) from error
Exception: None
from rave.
ozgurkara99
commented on August 29, 2024
it seems that you have not properly installed 'xformers' library to your environment. Please run
pip install xformers==0.0.20
to install it.
from rave.
SoftologyPro
commented on August 29, 2024
OK, thanks, that worked. Got a bit further. The model downloaded OK, then this error
zoedepth key error?
Traceback (most recent call last):
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 456, in call_prediction
output = await route_utils.call_process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
output = await app.get_blocks().process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1522, in process_api
result = await self.call_function(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1144, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
result = context.run(func, *args)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\utils.py", line 674, in wrapper
response = f(*args, **kwargs)
File "D:\Tests\RAVE\webui.py", line 143, in run
res_vid, control_vid = CN(input_dict)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 399, in __call__
img_batch, control_batch = self.process_image_batch(input_dict['image_pil_list'])
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 311, in process_image_batch
control_pil = self.preprocess_control_grid(image_pil)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 140, in preprocess_control_grid
list_of_pils = [pu.pixel_perfect_process(np.array(frame_pil, dtype='uint8'), self.preprocess_name) for frame_pil in list_of_image_pils]
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 140, in <listcomp>
list_of_pils = [pu.pixel_perfect_process(np.array(frame_pil, dtype='uint8'), self.preprocess_name) for frame_pil in list_of_image_pils]
File "D:\Tests\RAVE\utils\preprocesser_utils.py", line 211, in pixel_perfect_process
detected_map, _ = preprocessors_dict[p_name](input_image, res=preprocessor_resolution)
File "D:\Tests\RAVE\utils\preprocesser_utils.py", line 187, in zoe_depth
result = model_zoe_depth(img)
File "D:\Tests\RAVE\annotator\zoe\__init__.py", line 38, in __call__
self.load_model()
File "D:\Tests\RAVE\annotator\zoe\__init__.py", line 26, in load_model
conf = get_config("zoedepth", "infer")
File "D:\Tests\RAVE\annotator\zoe\zoedepth\utils\config.py", line 384, in get_config
version_name = overwrite_kwargs.get("version_name", config["version_name"])
KeyError: 'version_name'
Traceback (most recent call last):
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 456, in call_prediction
output = await route_utils.call_process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\route_utils.py", line 232, in call_process_api
output = await app.get_blocks().process_api(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1522, in process_api
result = await self.call_function(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\blocks.py", line 1144, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "D:\Tests\RAVE\voc_rave\lib\site-packages\anyio\_backends\_asyncio.py", line 807, in run
result = context.run(func, *args)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\utils.py", line 674, in wrapper
response = f(*args, **kwargs)
File "D:\Tests\RAVE\webui.py", line 143, in run
res_vid, control_vid = CN(input_dict)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 399, in __call__
img_batch, control_batch = self.process_image_batch(input_dict['image_pil_list'])
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 311, in process_image_batch
control_pil = self.preprocess_control_grid(image_pil)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 140, in preprocess_control_grid
list_of_pils = [pu.pixel_perfect_process(np.array(frame_pil, dtype='uint8'), self.preprocess_name) for frame_pil in list_of_image_pils]
File "D:\Tests\RAVE\pipelines\sd_controlnet_rave.py", line 140, in <listcomp>
list_of_pils = [pu.pixel_perfect_process(np.array(frame_pil, dtype='uint8'), self.preprocess_name) for frame_pil in list_of_image_pils]
File "D:\Tests\RAVE\utils\preprocesser_utils.py", line 211, in pixel_perfect_process
detected_map, _ = preprocessors_dict[p_name](input_image, res=preprocessor_resolution)
File "D:\Tests\RAVE\utils\preprocesser_utils.py", line 187, in zoe_depth
result = model_zoe_depth(img)
File "D:\Tests\RAVE\annotator\zoe\__init__.py", line 38, in __call__
self.load_model()
File "D:\Tests\RAVE\annotator\zoe\__init__.py", line 26, in load_model
conf = get_config("zoedepth", "infer")
File "D:\Tests\RAVE\annotator\zoe\zoedepth\utils\config.py", line 384, in get_config
version_name = overwrite_kwargs.get("version_name", config["version_name"])
KeyError: 'version_name'
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 501, in process_events
response = await self.call_prediction(awake_events, batch)
File "D:\Tests\RAVE\voc_rave\lib\site-packages\gradio\queueing.py", line 465, in call_prediction
raise Exception(str(error) if show_error else None) from error
Exception: None
from rave.
ozgurkara99
commented on August 29, 2024
@SoftologyPro Hey, could you please pull and try? I realized that I missed the json files required for depthzoe, now it should work. Thanks
from rave.
SoftologyPro
commented on August 29, 2024
OK, getting further now. It would be good to have an x/y steps for these stats.
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
img_size [384, 512]
It is now at a stage that has an estimated 1 hour to go? Is this normal? I will let it run and see if it completes.
5%|███████████▌ | 1/20 [03:21<1:03:41, 201.13s/it]
from rave.
ozgurkara99
commented on August 29, 2024
hey @SoftologyPro it is not normal, it is taking around 1-2s/it at most for the wolf video (512x512 sized video). I think you might be using CPU instead of GPU/CUDA.
from rave.
SoftologyPro
commented on August 29, 2024
I thought so too at first, but CPU is 2% and GPU is pegged at 100%.
Still going here (and I accidentally killed it, will let it run again and see if it finishes)
| 12/20 [42:04<28:09, 211.16s/it]
I've got xformers, accelerate and GPU torch.
from rave.
ozgurkara99
commented on August 29, 2024
what gpu are you using?
from rave.
SoftologyPro
commented on August 29, 2024
4090 24 GB
from rave.
SoftologyPro
commented on August 29, 2024
Wait, I just rebooted and restarted the wolf. Now only 7 minutes estimated. 17.22s/it
from rave.
ozgurkara99
commented on August 29, 2024
hey, here I am also using 4090 with 24 gbs, here it's around 3s/it. Maybe could you try increasing the batch size?
from rave.
SoftologyPro
commented on August 29, 2024
hey, here I am also using 4090 with 24 gbs, here it's around 3s/it. Maybe could you try increasing the batch size?
What batch size are you using?
from rave.
ozgurkara99
commented on August 29, 2024
it's 4 on my end
from rave.
SoftologyPro
commented on August 29, 2024
it's 4 on my end
4 here too. That is the default. You are running under Linux though right? May make a difference.
from rave.
SoftologyPro
commented on August 29, 2024
Raising batch size to 10 does not seem to help the speed.
Anyway, it works now. I will do some tetsts on other PCs.
from rave.
ozgurkara99
commented on August 29, 2024
Feel free to do tests, I am closing the issue.
from rave.
Related Issues (16)
- So many not found or No matching in requirements.txt HOT 4
- zoedepth/KeyError: 'version_name HOT 5
- Support for longer video length HOT 1
- Combine grid and shuffle latent to TokenFlow pipeline HOT 1
- Where can I find the code for WarpSSIM metric? HOT 2
- What is the minimum VRAM usage requirement of RAVE? HOT 2
- Processes continuously despite indicating its finished HOT 1
- RuntimeError: torch.cat(): expected a non-empty list of Tensors HOT 3
- local edit HOT 1
- OpenPose HOT 2
- Windows: How to save models within RAVE installation directory instead of huggingface cache HOT 1
- Does not work on windows 11. It created folder name using prompt. HOT 1
- What is the minimum requirement of memory for this to work HOT 3
- Adaptation for inpainting
- too slow to process a short video HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rave.