search

AUTOMATIC1111 / stable-diffusion-webui

Stable Diffusion web UI
GNU Affero General Public License v3.0
139.75k stars 26.49k forks source link

Error: bad shape for TensorRT #10890

Closed ExecuteAI closed 1 year ago

ExecuteAI commented 1 year ago

Is there an existing issue for this?

What happened?

User friendly error message: Error: bad shape for TensorRT input x: (2, 4, 67, 120). Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of . 2023-05-31 18:02:13,417 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK" 2023-05-31 18:02:13,427 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"

Steps to reproduce the problem

  1. Go to ....
  2. Press ....
  3. ...

What should have happened?

Deforum give me this and they say there is not support for TensorRT, but is it in the TensorRT model the problem is it is not them it is the NVIDIA product.

Commit where the problem happens

Bad Shape For TensorRT

What Python version are you running on ?

Python 3.10.x

What platforms do you use to access the UI ?

Windows

What device are you running WebUI on?

Nvidia GPUs (RTX 20 above)

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

NO

List of extensions

Deforum, TensorRT

Console logs

venv "C:\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Version: v1.3.0-72-gb957dcfe
Commit hash: b957dcfece29c84ac0cfcd5a69475ff8684c531f
Installing requirements

Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
ControlNet v1.1.204
ControlNet v1.1.204
Loading weights [6ce0161689] from C:\stable-diffusion-webui\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors
Create LRU cache (max_size=16) for preprocessor results.
Create LRU cache (max_size=16) for preprocessor results.
Creating model from config: C:\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
*Deforum ControlNet support: enabled*
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Create LRU cache (max_size=16) for preprocessor results.
Startup time: 34.2s (import torch: 11.3s, import gradio: 9.4s, import ldm: 2.2s, other imports: 4.8s, setup codeformer: 0.4s, load scripts: 4.1s, initialize extra networks: 0.2s, create ui: 1.4s, gradio launch: 0.4s).
Applying attention optimization: sdp-no-mem... done.
Textual inversion embeddings loaded(0):
Model loaded in 6.4s (load weights from disk: 0.6s, create model: 0.9s, apply weights to model: 1.1s, apply half(): 0.9s, move model to device: 2.6s, calculate empty prompt: 0.3s).
Deforum extension for auto1111 webui, v2.4b
Git commit: 87340181
Saving animation frames to:
C:\stable-diffusion-webui\outputs/img2img-images\Deforum_20230531180203
Loading MiDaS model from dpt_large-midas-2f21e586.pt...
Animation frame: 0/600
Seed: 912572441
Prompt: beautiful teeth, aarhus, straight teeth, Scandinavian people, 2020 Marsterpiece, happy family, scandinavian, baby in a cradle, mohark, rebel, smiling, laughing, Aarhus, outside, golden hour, ultra high detail, 8k, unreal engine
Neg Prompt: nsfw, nude, split screen, ugly teeth
Not using an init image (doing pure txt2img)
╭─────┬───┬───────┬────┬────┬────┬────┬────┬────╮
│Steps│CFG│Denoise│Tr X│Tr Y│Tr Z│Ro X│Ro Y│Ro Z│
├─────┼───┼───────┼────┼────┼────┼────┼────┼────┤
│ 25  │7.0│   0   │0.65│ 0  │0.2 │ 0  │ 0  │ 0  │
╰─────┴───┴───────┴────┴────┴────┴────┴────┴────╯
Activating unet: [TRT] v1-5-pruned-emaonly
[05/31/2023-18:02:12] [TRT] [W] TensorRT was linked against cuDNN 8.9.0 but loaded cuDNN 8.7.0
[05/31/2023-18:02:12] [TRT] [W] TensorRT was linked against cuDNN 8.9.0 but loaded cuDNN 8.7.0
[05/31/2023-18:02:13] [TRT] [W] CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage and speed up TensorRT initialization. See "Lazy Loading" section of CUDA documentation https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#lazy-loading
  0%|                                                                                           | 0/25 [00:00<?, ?it/s][05/31/2023-18:02:13] [TRT] [E] 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::validateInputBindings::2082] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::validateInputBindings::2082, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [2,4,67,120] for bindings[0] exceed min ~ max range at index 2, maximum dimension in profile is 64, minimum dimension in profile is 64, but supplied dimension is 67.
)
  0%|                                                                                           | 0/25 [00:00<?, ?it/s]

*START OF TRACEBACK*
Traceback (most recent call last):
  File "C:\stable-diffusion-webui\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\run_deforum.py", line 76, in run_deforum
    render_animation(args, anim_args, video_args, parseq_args, loop_args, controlnet_args, root)
  File "C:\stable-diffusion-webui\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\render.py", line 547, in render_animation
    image = generate(args, keys, anim_args, loop_args, controlnet_args, root, frame_idx, sampler_name=scheduled_sampler_name)
  File "C:\stable-diffusion-webui\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\generate.py", line 55, in generate
    return generate_inner(args, keys, anim_args, loop_args, controlnet_args, root, frame, sampler_name)
  File "C:\stable-diffusion-webui\extensions\deforum-for-automatic1111-webui\scripts\deforum_helpers\generate.py", line 207, in generate_inner
    processed = processing.process_images(p_txt)
  File "C:\stable-diffusion-webui\modules\processing.py", line 611, in process_images
    res = process_images_inner(p)
  File "C:\stable-diffusion-webui\extensions\sd-webui-controlnet\scripts\batch_hijack.py", line 42, in processing_process_images_hijack
    return getattr(processing, '__controlnet_original_process_images_inner')(p, *args, **kwargs)
  File "C:\stable-diffusion-webui\modules\processing.py", line 731, in process_images_inner
    samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
  File "C:\stable-diffusion-webui\modules\processing.py", line 979, in sample
    samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
  File "C:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 433, in sample
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "C:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 275, in launch_sampling
    return func()
  File "C:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 433, in <lambda>
    samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
  File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "C:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 518, in sample_dpmpp_2s_ancestral
    denoised = model(x, sigmas[i] * s_in, **extra_args)
  File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 155, in forward
    x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict([cond_in], image_cond_in))
  File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 112, in forward
    eps = self.get_eps(input * c_in, self.sigma_to_t(sigma), **kwargs)
  File "C:\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\external.py", line 138, in get_eps
    return self.inner_model.apply_model(*args, **kwargs)
  File "C:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 17, in <lambda>
    setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))
  File "C:\stable-diffusion-webui\modules\sd_hijack_utils.py", line 28, in __call__
    return self.__orig_func(*args, **kwargs)
  File "C:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 858, in apply_model
    x_recon = self.model(x_noisy, t, **cond)
  File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1335, in forward
    out = self.diffusion_model(x, t, context=cc)
  File "C:\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\stable-diffusion-webui\modules\sd_unet.py", line 89, in UNetModel_forward
    return current_unet.forward(x, timesteps, context, *args, **kwargs)
  File "C:\stable-diffusion-webui\extensions\stable-diffusion-webui-tensorrt\scripts\trt.py", line 86, in forward
    self.infer({"x": x, "timesteps": timesteps, "context": context})
  File "C:\stable-diffusion-webui\extensions\stable-diffusion-webui-tensorrt\scripts\trt.py", line 69, in infer
    self.allocate_buffers(feed_dict)
  File "C:\stable-diffusion-webui\extensions\stable-diffusion-webui-tensorrt\scripts\trt.py", line 63, in allocate_buffers
    raise Exception(f'bad shape for TensorRT input {binding}: {tuple(shape)}')
Exception: bad shape for TensorRT input x: (2, 4, 67, 120)
*END OF TRACEBACK*

User friendly error message:
Error: bad shape for TensorRT input x: (2, 4, 67, 120). Check your schedules/ init values please. Also make sure you don't have a backwards slash in any of your PATHs - use / instead of \.
2023-05-31 18:02:13,417 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
2023-05-31 18:02:13,427 - httpx - INFO - HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"

Additional information

No response

akx commented 1 year ago

This is a https://github.com/AUTOMATIC1111/stable-diffusion-webui-tensorrt specific error; report it on the extension's tracker.