lllyasviel
Problem with controlnet
I made this post a month ago: https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/1140
the problem is still present, so I cannot work with forge
I add the log: is it due to the message : "DeprecationWarning: pkg_resources is deprecated as an API" ?? if yes, what should I do? I already tried to re-install
Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Version: f2.0.1v1.10.1-previous-531-g210af4f8 Commit hash: 210af4f80406f78a67e1c35a64a6febdf1200a82 E:\StableDiffusion\Packages\Stable Diffusion WebUI Forge\extensions\sd-webui-infinite-image-browsing\install.py:3: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html import pkg_resources E:\StableDiffusion\Packages\Stable Diffusion WebUI Forge\extensions-builtin\forge_legacy_preprocessors\install.py:2: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html import pkg_resources E:\StableDiffusion\Packages\Stable Diffusion WebUI Forge\extensions-builtin\sd_forge_controlnet\install.py:2: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html import pkg_resources Launching Web UI with arguments: --cuda-malloc --gradio-allowed-path 'E:\StableDiffusion\Images' Using cudaMallocAsync backend. Total VRAM 8192 MB, total RAM 32680 MB pytorch version: 2.3.1+cu121 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 2060 SUPER : cudaMallocAsync VAE dtype preferences: [torch.float32] -> torch.float32 CUDA Using Stream: False Using pytorch cross attention Using pytorch attention for VAE ControlNet preprocessor location: E:\StableDiffusion\Packages\Stable Diffusion WebUI Forge\models\ControlNetPreprocessor 2024-09-16 13:27:08,909 - ControlNet - INFO - ControlNet UI callback registered. Model selected: {'checkpoint_info': {'filename': 'E:\StableDiffusion\Packages\Stable Diffusion WebUI Forge\models\Stable-diffusion\Flux\flux1-dev-bnb-nf4-v2.safetensors', 'hash': 'f0770152'}, 'additional_modules': [], 'unet_storage_dtype': None} Using online LoRAs in FP16: False Running on local URL: http://127.0.0.1:7861
To create a public link, set share=True in launch().
IIB Database file has been successfully backed up to the backup folder.
Startup time: 84.0s (prepare environment: 23.7s, launcher: 0.2s, import torch: 43.7s, initialize shared: 0.9s, other imports: 4.4s, list SD models: 1.3s, load scripts: 6.0s, initialize extra networks: 0.1s, create ui: 2.9s, gradio launch: 1.4s, app_started_callback: 0.1s).
I have the same deprecated warnings but my forge works regardless. I don't know if this has any impact.
I don't get those deprecation warnings, but they shouldn't be relevant. I do get, as expected, identical results in img2img and inpaint upload. The depth map control image is correct for the source, and generations follow the control image. Are you using low Control Weight or Timestep Range? Or a mask?
I don't get those deprecation warnings, but they shouldn't be relevant. I do get, as expected, identical results in img2img and inpaint upload. The depth map control image is correct for the source, and generations follow the control image. Are you using low Control Weight or Timestep Range? Or a mask?
i use a mask