search

anapnoe / stable-diffusion-webui-ux

Stable Diffusion web UI UX
GNU Affero General Public License v3.0
970 stars 58 forks source link

[Bug]: Fresh Install - not working #117

Closed jurandfantom closed 1 year ago

jurandfantom commented 1 year ago

Is there an existing issue for this?

What happened?

Hi there, to be honest I wish to provide more informations, steps and anything, but I have no clue about what could be even wrong here. Windows 10, RTX 4090 Just git clone repo, installed it, used "--skip-torch-cuda-test" as it was suggested by installation, and run UX as it should (looks great!). Only thing that was done from here, was pick realistic vision 2 model and use prompt - then just click generate.

Steps to reproduce the problem

  1. install repo
  2. add "--skip-torch-cuda-test" to bat file
  3. change model to realistic vision
  4. enter prompt
  5. generate

What should have happened?

.

Commit where the problem happens

https://github.com/anapnoe/stable-diffusion-webui-ux/commit/e2d23b46f41dadae72e01630dbe89a79bd2dbc5d

What platforms do you use to access the UI ?

Windows

What browsers do you use to access the UI ?

Mozilla Firefox

Command Line Arguments

set COMMANDLINE_ARGS= --skip-torch-cuda-test

List of extensions

No

Console logs

Running on local URL:  http://127.0.0.1:7861

To create a public link, set `share=True` in `launch()`.
Startup time: 3.1s (load scripts: 0.4s, reload script modules: 0.1s, list SD models: 0.7s, create ui: 1.6s, gradio launch: 0.2s).
Error completing request
Arguments: ('task(jn77o64mh6wimmh)', 'green man', '', [], 20, 15, False, False, 78, 36, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0) {}
Traceback (most recent call last):
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\call_queue.py", line 57, in f
    res = list(func(*args, **kwargs))
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\processing.py", line 515, in process_images
    res = process_images_inner(p)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\processing.py", line 658, in process_images_inner
    uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps * step_multiplier, cached_uc)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\processing.py", line 597, in get_conds_with_caching
    cache[1] = function(shared.sd_model, required_prompts, steps)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\prompt_parser.py", line 140, in get_learned_conditioning
    conds = model.get_learned_conditioning(texts)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 669, in get_learned_conditioning
    c = self.cond_stage_model(c)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\sd_hijack_clip.py", line 229, in forward
    z = self.process_tokens(tokens, multipliers)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\sd_hijack_clip.py", line 254, in process_tokens
    z = self.encode_with_transformers(tokens)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\sd_hijack_clip.py", line 302, in encode_with_transformers
    outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 811, in forward
    return self.text_model(
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 721, in forward
    encoder_outputs = self.encoder(
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 650, in forward
    layer_outputs = encoder_layer(
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 378, in forward
    hidden_states = self.layer_norm1(hidden_states)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\normalization.py", line 190, in forward
    return F.layer_norm(
  File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\functional.py", line 2515, in layer_norm
    return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

Additional information

No response

anapnoe commented 1 year ago

no issue with the arg --skip-torch-cuda-test tested with RTX 2070, win10, chrome does it work with other models? does it work if you remove the --skip-torch-cuda-test? did you test in other browser Chrome? this would provide some more insight

vit-cerny commented 1 year ago

Me too, same error, rtx 2060, fix from creator above doesnt work.

anapnoe commented 1 year ago

according to this restart your pc https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/7522

jurandfantom commented 1 year ago

I was about to say sorry for late reply, but I see topic was closed just after 1 day (fells like 3) - don't be so hasty anapnoe :)

Checked all suggested things after PC restart and git pull

1) does it work with other models? Nope - same error after change model. Additionally here is log afer change one model into another (without generation, just pick from list)

Received inputs: ["Semi-real\SR_05_ProtoGen_C-V53Photorealism_ATFSilver.safetensors"] Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\routes.py", line 399, in run_predict output = await app.get_blocks().process_api( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1297, in process_api inputs = self.preprocess_data(fn_index, inputs, state) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1133, in preprocess_data self.validate_inputs(fn_index, inputs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1120, in validate_inputs raise ValueError( ValueError: An event handler didn't receive enough input values (needed: 2, got: 1). Check if the event handler calls a Javascript function, and make sure its return value is correct. Wanted inputs: [dropdown, label] Received inputs: ["Test\edgeOfRealism_edgeOfRealismNOVAE.safetensors"]

2) does it work if you remove the --skip-torch-cuda-test? venv "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\Scripts\Python.exe" Python 3.10.9 | packaged by conda-forge | (main, Jan 11 2023, 15:15:40) [MSC v.1916 64 bit (AMD64)] Commit hash: c647b27a5005d9ce8bac5d7776ef9374c28890b8 Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\launch.py", line 352, in prepare_environment() File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\launch.py", line 257, in prepare_environment run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'") File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\launch.py", line 120, in run_python return run(f'"{python}" -c "{code}"', desc, errdesc) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\launch.py", line 96, in run raise RuntimeError(message) RuntimeError: Error running command. Command: "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\Scripts\python.exe" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'" Error code: 1 stdout: stderr: Traceback (most recent call last): File "", line 1, in AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check

Press any key to continue . . .

3) did you test in other browser Chrome? Firefox, Chrome, Opera - same situation.

Response is as follow:

venv "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\Scripts\Python.exe" Python 3.10.9 | packaged by conda-forge | (main, Jan 11 2023, 15:15:40) [MSC v.1916 64 bit (AMD64)] Commit hash: c647b27a5005d9ce8bac5d7776ef9374c28890b8 Installing requirements Launching Web UI with arguments: --skip-torch-cuda-test Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled No module 'xformers'. Proceeding without it. Loading weights [0f79788993] from E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\models\Stable-diffusion\Realistic\R_02_EldenRing-v3-pruned.safetensors Creating model from config: E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\configs\v1-inference.yaml LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 859.52 M params. Applying cross attention optimization (InvokeAI). Textual inversion embeddings loaded(0): Model loaded in 71.2s (load weights from disk: 2.1s, create model: 1.0s, apply weights to model: 67.2s, apply half(): 0.7s). Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch(). Startup time: 114.4s (import torch: 10.8s, import gradio: 7.1s, import ldm: 3.0s, other imports: 6.2s, list SD models: 3.8s, setup codeformer: 0.4s, list builtin upscalers: 0.1s, load scripts: 7.8s, load SD checkpoint: 71.4s, create ui: 3.5s, gradio launch: 0.4s). Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\routes.py", line 399, in run_predict output = await app.get_blocks().process_api( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1297, in process_api inputs = self.preprocess_data(fn_index, inputs, state) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1133, in preprocess_data self.validate_inputs(fn_index, inputs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1120, in validate_inputs raise ValueError( ValueError: An event handler (f) didn't receive enough input values (needed: 176, got: 0). Check if the event handler calls a Javascript function, and make sure its return value is correct. Wanted inputs: [checkbox, textbox, textbox, checkbox, checkbox, textbox, checkbox, checkbox, checkbox, slider, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, slider, checkbox, checkbox, number, number, number, checkbox, checkbox, checkbox, checkbox, textbox, checkbox, textbox, textbox, textbox, textbox, textbox, textbox, textbox, textbox, textbox, checkbox, checkbox, checkbox, textbox, slider, slider, slider, checkboxgroup, dropdown, slider, slider, slider, checkbox, slider, slider, radio, slider, checkbox, checkbox, slider, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, textbox, textbox, number, number, checkbox, checkbox, checkbox, number, label, slider, slider, dropdown, checkbox, slider, slider, checkbox, checkbox, colorpicker, checkbox, checkbox, checkbox, slider, slider, checkbox, number, checkboxgroup, radio, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, slider, slider, slider, number, checkboxgroup, slider, checkbox, checkbox, checkbox, textbox, slider, textbox, checkbox, slider, slider, checkbox, dropdown, dropdown, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, checkbox, textbox, checkbox, checkbox, checkbox, checkbox, checkbox, slider, slider, textbox, textbox, dropdown, textbox, textbox, textbox, radio, textbox, radio, checkbox, checkbox, dropdown, dropdown, checkbox, checkbox, checkbox, slider, radio, radio, number, radio, checkboxgroup, slider, slider, radio, slider, slider, slider, slider, number, checkbox, radio, radio, slider, checkbox, dropdown, dropdown, slider, label, label, label, label] Received inputs: [] Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\routes.py", line 399, in run_predict output = await app.get_blocks().process_api( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1297, in process_api inputs = self.preprocess_data(fn_index, inputs, state) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1133, in preprocess_data self.validate_inputs(fn_index, inputs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1120, in validate_inputs raise ValueError( ValueError: An event handler didn't receive enough input values (needed: 1, got: 0). Check if the event handler calls a Javascript function, and make sure its return value is correct. Wanted inputs: [dropdown] Received inputs: [] Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\routes.py", line 399, in run_predict output = await app.get_blocks().process_api( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1297, in process_api inputs = self.preprocess_data(fn_index, inputs, state) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1133, in preprocess_data self.validate_inputs(fn_index, inputs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\blocks.py", line 1120, in validate_inputs raise ValueError( ValueError: An event handler (f) didn't receive enough input values (needed: 13, got: 0). Check if the event handler calls a Javascript function, and make sure its return value is correct. Wanted inputs: [label, dropdown, dropdown, dropdown, radio, slider, checkbox, textbox, radio, radio, dropdown, textbox, checkbox] Received inputs: [] ERROR: Exception in ASGI application Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 428, in run_asgi result = await app( # type: ignore[func-returns-value] File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 78, in call return await self.app(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\applications.py", line 273, in call await super().call(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\errors.py", line 184, in call raise exc File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\errors.py", line 162, in call await self.app(scope, receive, _send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\gzip.py", line 24, in call await responder(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\gzip.py", line 44, in call await self.app(scope, receive, self.send_with_gzip) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\exceptions.py", line 79, in call raise exc File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\exceptions.py", line 68, in call await self.app(scope, receive, sender) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 21, in call raise e File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 18, in call await self.app(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\routing.py", line 718, in call await route.handle(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\routing.py", line 276, in handle await self.app(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\routing.py", line 66, in app response = await func(request) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\routing.py", line 237, in app raw_response = await run_endpoint_function( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\routing.py", line 163, in run_endpoint_function return await dependant.call(values) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\routes.py", line 465, in predict if app.get_blocks().dependencies[fn_index_inferred]["cancels"]: IndexError: list index out of range ERROR: Exception in ASGI application Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 428, in run_asgi result = await app( # type: ignore[func-returns-value] File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\uvicorn\middleware\proxy_headers.py", line 78, in call return await self.app(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\applications.py", line 273, in call await super().call(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\errors.py", line 184, in call raise exc File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\errors.py", line 162, in call await self.app(scope, receive, _send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\gzip.py", line 24, in call await responder(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\gzip.py", line 44, in call await self.app(scope, receive, self.send_with_gzip) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\exceptions.py", line 79, in call raise exc File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\middleware\exceptions.py", line 68, in call await self.app(scope, receive, sender) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 21, in call raise e File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\middleware\asyncexitstack.py", line 18, in call await self.app(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\routing.py", line 718, in call await route.handle(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\routing.py", line 276, in handle await self.app(scope, receive, send) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\starlette\routing.py", line 66, in app response = await func(request) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\routing.py", line 237, in app raw_response = await run_endpoint_function( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\fastapi\routing.py", line 163, in run_endpoint_function return await dependant.call(values) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\gradio\routes.py", line 465, in predict if app.get_blocks().dependencies[fn_index_inferred]["cancels"]: IndexError: list index out of range Error completing request Arguments: ('task(ij2u17557vqhdgz)', 'green man', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0) {} Traceback (most recent call last): File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\call_queue.py", line 57, in f res = list(func(*args, kwargs)) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\call_queue.py", line 37, in f res = func(*args, kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\txt2img.py", line 56, in txt2img processed = process_images(p) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\processing.py", line 515, in process_images res = process_images_inner(p) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\processing.py", line 658, in process_images_inner uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps step_multiplier, cached_uc) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\processing.py", line 597, in get_conds_with_caching cache[1] = function(shared.sd_model, required_prompts, steps) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\prompt_parser.py", line 140, in get_learned_conditioning conds = model.get_learned_conditioning(texts) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 669, in get_learned_conditioning c = self.cond_stage_model(c) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\sd_hijack_clip.py", line 229, in forward z = self.process_tokens(tokens, multipliers) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\sd_hijack_clip.py", line 254, in process_tokens z = self.encode_with_transformers(tokens) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\modules\sd_hijack_clip.py", line 302, in encode_with_transformers outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 811, in forward return self.text_model( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 721, in forward encoder_outputs = self.encoder( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, *kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 650, in forward layer_outputs = encoder_layer( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(args, kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 378, in forward hidden_states = self.layer_norm1(hidden_states) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl return forward_call(*args, **kwargs) File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\modules\normalization.py", line 190, in forward return F.layer_norm( File "E:\Magazyn\Grafika\AI\stable-diffusion-webui-ux\venv\lib\site-packages\torch\nn\functional.py", line 2515, in layer_norm return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled) RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'

anapnoe commented 1 year ago

issues can be reopen can you put --skip-torch-cuda-test --no-half in command args? it seems that for some reason all params are empty this is rather strange issue

anapnoe commented 1 year ago

you can also check the latest commit and report if something has change

anapnoe commented 1 year ago

close this one cant reproduce

jurandfantom commented 1 year ago

confirmed - all works now. (sorry, totally forgot to check things when you ask me ) - great job