StreamDiffusionTD 0.1.8 🚀🖼️ [ TOX ]
Added 2024-04-21 22:22:54 +0000 UTC[ EDIT - 0.1.9 Version fixes possible error when switching resolutions + issues with finding shared memory ]
Changelog / announcement - www.patreon.com/posts/streamdiffusiont-102788281
Upgrade Guide
Similar to previous version, just copy and paste your Basefolder parameter ( and depending on your setup change other settings in the operator) and it should load your previous working model list. Once you select a Main SD Model, you should be ready to go.
Comments
During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\streamdiffusionTD\wrapper_td.py", line 460, in _load_model pipe: StableDiffusionPipeline = StableDiffusionPipeline.from_pretrained( File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1090, in from_pretrained cached_folder = cls.download( File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1649, in download info = model_info( File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\huggingface_hub\hf_api.py", line 2300, in model_info r = get_session().get(path, headers=headers, timeout=timeout, params=params) File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 600, in get return self.request("GET", url, **kwargs) File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 587, in request resp = self.send(prep, **send_kwargs) File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 701, in send r = adapter.send(request, **kwargs) File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_http.py", line 66, in send return super().send(request, *args, **kwargs) File "C:\Users\crist\Desktop\ST TEST\SD\StreamDiffusion\venv\lib\site-packages\requests\adapters.py", line 547, in send raise ConnectionError(err, request=request) requests.exceptions.ConnectionError: (ProtocolError('Connection aborted.', ConnectionResetError(10054, 'Se ha forzado la interrupción de una conexión existente por el host remoto', None, 10054, None)), '(Request ID: e7d752c3-ee77-40e2-a23f-7c2e6424caaa)') Model load has failed. Doesn't exist.
Cristopher Villarreal
2024-05-15 19:05:18 +0000 UTCI have a similar problem, any idea what it could be?
Cristopher Villarreal
2024-05-15 19:04:14 +0000 UTCtenta reinstalar e na aba models direciona ela pra pasta do streamdiffusion/models. ce pode também tentar reinstalar do 0 o erro que você ta tendo é que o localhost tá cortando a conexão, vê também se o teu touchdesigner tá recebendo o sinal Osc
Sarah Ahab
2024-05-15 11:12:10 +0000 UTCIm getting this error in the last part of installation Loading SD model: stabilityai/sd-turbo Traceback (most recent call last): File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen httplib_response = self._make_request( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 386, in _make_request self._validate_conn(conn) File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 1042, in _validate_conn conn.connect() File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connection.py", line 414, in connect self.sock = ssl_wrap_socket( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\util\ssl_.py", line 449, in ssl_wrap_socket ssl_sock = _ssl_wrap_socket_impl( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\util\ssl_.py", line 493, in _ssl_wrap_socket_impl return ssl_context.wrap_socket(sock, server_hostname=server_hostname) File "C:\Users\guilh\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 512, in wrap_socket return self.sslsocket_class._create( File "C:\Users\guilh\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1070, in _create self.do_handshake() File "C:\Users\guilh\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1341, in do_handshake self._sslobj.do_handshake() ConnectionResetError: [WinError 10054] Foi forçado o cancelamento de uma conexão existente pelo host remoto During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\SD\StreamDiffusion\venv\lib\site-packages\requests\adapters.py", line 489, in send resp = conn.urlopen( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen retries = retries.increment( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\util\retry.py", line 550, in increment raise six.reraise(type(error), error, _stacktrace) File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\packages\six.py", line 769, in reraise raise value.with_traceback(tb) File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen httplib_response = self._make_request( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 386, in _make_request self._validate_conn(conn) File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connectionpool.py", line 1042, in _validate_conn conn.connect() File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\connection.py", line 414, in connect self.sock = ssl_wrap_socket( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\util\ssl_.py", line 449, in ssl_wrap_socket ssl_sock = _ssl_wrap_socket_impl( File "C:\SD\StreamDiffusion\venv\lib\site-packages\urllib3\util\ssl_.py", line 493, in _ssl_wrap_socket_impl return ssl_context.wrap_socket(sock, server_hostname=server_hostname) File "C:\Users\guilh\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 512, in wrap_socket return self.sslsocket_class._create( File "C:\Users\guilh\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1070, in _create self.do_handshake() File "C:\Users\guilh\AppData\Local\Programs\Python\Python310\lib\ssl.py", line 1341, in do_handshake self._sslobj.do_handshake() urllib3.exceptions.ProtocolError: ('Connection aborted.', ConnectionResetError(10054, 'Foi forçado o cancelamento de uma conexão existente pelo host remoto', None, 10054, None)) During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\SD\StreamDiffusion\streamdiffusionTD\wrapper_td.py", line 460, in _load_model pipe: StableDiffusionPipeline = StableDiffusionPipeline.from_pretrained( File "C:\SD\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1090, in from_pretrained cached_folder = cls.download( File "C:\SD\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1649, in download info = model_info( File "C:\SD\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "C:\SD\StreamDiffusion\venv\lib\site-packages\huggingface_hub\hf_api.py", line 2300, in model_info r = get_session().get(path, headers=headers, timeout=timeout, params=params) File "C:\SD\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 600, in get return self.request("GET", url, **kwargs) File "C:\SD\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 587, in request resp = self.send(prep, **send_kwargs) File "C:\SD\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 701, in send r = adapter.send(request, **kwargs) File "C:\SD\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_http.py", line 66, in send return super().send(request, *args, **kwargs) File "C:\SD\StreamDiffusion\venv\lib\site-packages\requests\adapters.py", line 547, in send raise ConnectionError(err, request=request) requests.exceptions.ConnectionError: (ProtocolError('Connection aborted.', ConnectionResetError(10054, 'Foi forçado o cancelamento de uma conexão existente pelo host remoto', None, 10054, None)), '(Request ID: 293269d8-2db5-4710-aa37-f4b062449cee)') Model load has failed. Doesn't exist. Can you help please????
Guilherme Bretas
2024-05-03 14:29:22 +0000 UTChi! Im really new at this
Guilherme Bretas
2024-05-03 14:27:54 +0000 UTCthis don't affect image generation...
Bao Nguyen
2024-05-02 15:24:20 +0000 UTCHi There !! I absolutley love your videos - following your instruction video I have gotten to the last stage of first running the .tox and it is coming up with an error message about the matching triton not being avaliable. In summary it is SAYING 'Error caught was: No module named 'triton' Config file path: C:\Touch\TestInstall\StreamDiffusion\streamdiffusionTD\stream_config.json' It is also saying A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' Could you please provide me with any advice about what triton is and how I might fix this error message - thanks so much for all your time and effort !
Milly Yates
2024-05-01 06:52:57 +0000 UTCThanks for the quick reply, can’t wait to check it out 🫰🏻🍀
Mercan
2024-04-30 15:37:59 +0000 UTCis posted in the discord. I will post an update today with a few other tiny fixes + mac support
dotsimulate
2024-04-30 15:32:33 +0000 UTCHi, i am actually looking for the .tox file for the mac. Couldn't find it, does anyone know how can i access thank you.
Mercan
2024-04-30 08:52:28 +0000 UTCNo entirely sure. I believe there was someone on the discord that figured out the issue. let me check
dotsimulate
2024-04-29 23:30:35 +0000 UTCHi I got this error when i hit doanload/update SD : No internet connection detected, i am phscially in china, but has already change my git global config to the proxies. did i miss somthing here?
Yuxi Cao (JAMES)
2024-04-29 15:19:26 +0000 UTCHello John, thank you :) as a newbie I'm a bit lost, can you give me the link? Is it in Patreon or in Github? Thanks a lot
Jean Dupont
2024-04-25 16:51:51 +0000 UTCNote: CUDA 12.1 users need to make a manual change in the StreamDiffusion repository. For details, visit the troubleshoot
John Tony
2024-04-25 16:28:26 +0000 UTCHello since version 0.1.7 I cannot run anything , I always have this error: Traceback (most recent call last): File "/project1/StreamDiffusionTD/extensionParExec", line 14, in onPulse File "/project1/StreamDiffusionTD/StreamDiffusionExt", line 248, in Startstream File "/project1/StreamDiffusionTD/StreamDiffusionExt", line 960, in copy_ndi_code File "C:\Program Files\Derivative\TouchDesigner.2023.11600\bin\Lib\encodings\cp1252.py", line 19, in encode return codecs.charmap_encode(input,self.errors,encoding_table)[0] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ UnicodeEncodeError: 'charmap' codec can't encode characters in position 13169-13178: character maps to I'm running on windows11 - TD build: 2023.11600 version 0.1.5 works fine, any ideas?
Jean Dupont
2024-04-25 15:32:58 +0000 UTCThanks so much! Also looking forward to this evening's talk in Berlin! See you there :)
Raquel F.
2024-04-25 10:30:24 +0000 UTCI met some problem, everything gonna be ok in SD1.0.1,but when I update the version,something is mistake. The program still worked,but the Lora Models couldn't load. ERROR loading LoRA Models: Error(s) in loading state_dict for UNet2DConditionModel: size mismatch for down_blocks.0.attentions.0.proj_in.lora_A.default_0.weight: copying a param with shape torch.Size([16, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 320]). size mismatch for down_blocks.0.attentions.0.proj_in.lora_B.default_0.weight: copying a param with shape torch.Size([320, 16, 1, 1]) from checkpoint, the shape in current model is torch.Size([320, 16]). size mismatch for down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.lora_A.default_0.weight: copying a param with shape torch.Size([16, 768]) from checkpoint, the shape in current model is torch.Size([16, 1024]). size mismatch for down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.lora_A.default_0.weight: copying a param with shape torch.Size([16, 768]) from checkpoint, the shape in current model is torch.Size([16, 1024]).
Baiii L
2024-04-23 19:02:30 +0000 UTCVery cool, thank you!!
Jason Beyers
2024-04-22 23:29:37 +0000 UTCYes, I think so. 0.1.9 will handle the buffer in / out better in general. also limits resolution to multiplier of 8 to align with diffuser pipeline
dotsimulate
2024-04-22 23:28:25 +0000 UTCI don't think Mac will give comparable speeds. But someone in the discord has streamdiffusion repo running on mac. Should be possible to manage getting it to work with the op, although at slower fps.
dotsimulate
2024-04-22 23:22:50 +0000 UTCThanks so much! If we haven’t run into the 0.1.8 issues you noted, would you still recommend upgrading?
Jason Beyers
2024-04-22 23:21:07 +0000 UTCdo we know if anyone is working on/had any success getting this workin for MPS. Workin on a m2 ultra mac studio and I know right now its theoretically only capable of working on nvidia gpus but ive seen some people having success getting the demos working on MPS
Troy Pereira
2024-04-22 22:40:05 +0000 UTC
