ninjaneural / webui Goto Github PK

안녕하세요,

제가 여태 터널링 없이 하는 버젼을 잘 이용해 왔는데 최근 들어서 사진 한두장 뽑으면
Something went wrong
JSON.parse: unexpected character at line 1 column 1 of the JSON data

이라는 오류가 뜨고 다시 처음부터 실행해야하는 번거로움이 생겼습니다. (한 3~4일 전부터?)

혹시 이거 어떻게 하면 수정 가능한지 아시나요?

감사합니다.

Hello! Could you please provide expmixLine_v20-no-ema.safetensors ? I would really appreciate it!
Because it can no longer be downloaded from the provided link:
https://huggingface.co/AIARTCHAN/expmixLine_v2/resolve/main/expmixLine_v20-no-ema.safetensors

실행 후 주소 클릭 시 403에러 메시지와 함께 webui 접속 오류문제가 발생합니다. 확인부탁드립니다.

brabeautiful_realistic colab 설치버전으로 설치를 완료한 후,
안내에 따라 run.ipynb 를 구글드라이브에 올리고 코랩으로 실행했는데요,
아래와 같은 에러메시지가 뜨면서 열리지 않습니다.
확인 부탁드립니다.

fatal: No names found, cannot describe anything.
Python 3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]
Version: 1.6.0
Commit hash: 5ef669de080814067961f28357256e8fe27544f4
Fetching updates for K-diffusion...
Checking out commit for K-diffusion with hash: ab527a9a6d347f364e3d185ba6d714e22d80cb3c...
error: Your local changes to the following files would be overwritten by checkout:
convert_for_inference.py
sample.py
sample_clip_guided.py
train.py
Please commit your changes or stash them before you switch branches.
Aborting
Couldn't checkout commit ab527a9a6d347f364e3d185ba6d714e22d80cb3c for K-diffusion, attempting autofix...
Fetching all contents for K-diffusion
error: unknown option `refetch'
usage: git fetch [] [ [...]]
or: git fetch []
or: git fetch --multiple [] [( | )...]
or: git fetch --all []

-v, --verbose         be more verbose
-q, --quiet           be more quiet
--all                 fetch from all remotes
--set-upstream        set upstream for git pull/fetch
-a, --append          append to .git/FETCH_HEAD instead of overwriting
--atomic              use atomic transaction to update references
--upload-pack <path>  path to upload pack on remote end
-f, --force           force overwrite of local reference
-m, --multiple        fetch from multiple remotes
-t, --tags            fetch all tags and associated objects
-n                    do not fetch all tags (--no-tags)
-j, --jobs <n>        number of submodules fetched in parallel
--prefetch            modify the refspec to place all refs within refs/prefetch/
-p, --prune           prune remote-tracking branches no longer on remote
-P, --prune-tags      prune local tags no longer on remote and clobber changed tags
--recurse-submodules[=<on-demand>]
                      control recursive fetching of submodules
--dry-run             dry run
--write-fetch-head    write fetched references to the FETCH_HEAD file
-k, --keep            keep downloaded pack
-u, --update-head-ok  allow updating of HEAD ref
--progress            force progress reporting
--depth <depth>       deepen history of shallow clone
--shallow-since <time>
                      deepen history of shallow repository based on time
--shallow-exclude <revision>
                      deepen history of shallow clone, excluding rev
--deepen <n>          deepen history of shallow clone
--unshallow           convert to a complete repository
--update-shallow      accept refs that update .git/shallow
--refmap <refmap>     specify fetch refmap
-o, --server-option <server-specific>
                      option to transmit
-4, --ipv4            use IPv4 addresses only
-6, --ipv6            use IPv6 addresses only
--negotiation-tip <revision>
                      report that we have only objects reachable from this object
--negotiate-only      do not fetch a packfile; instead, print ancestors of negotiation tips
--filter <args>       object filtering
--auto-maintenance    run 'maintenance --auto' after fetching
--auto-gc             run 'maintenance --auto' after fetching
--show-forced-updates
                      check for forced-updates on all updated branches
--write-commit-graph  write the commit-graph after fetching
--stdin               accept refspecs from stdin

Traceback (most recent call last):
File "/content/drive/MyDrive/install/launch.py", line 48, in
main()
File "/content/drive/MyDrive/install/launch.py", line 39, in main
prepare_environment()
File "/content/drive/MyDrive/install/modules/launch_utils.py", line 382, in prepare_environment
git_clone(k_diffusion_repo, repo_dir('k-diffusion'), "K-diffusion", k_diffusion_commit_hash)
File "/content/drive/MyDrive/install/modules/launch_utils.py", line 181, in git_clone
run_git(dir, name, f'checkout {commithash}', f"Checking out commit for {name} with hash: {commithash}...", f"Couldn't checkout commit {commithash} for {name}", live=True)
File "/content/drive/MyDrive/install/modules/launch_utils.py", line 160, in run_git
git_fix_workspace(dir, name)
File "/content/drive/MyDrive/install/modules/launch_utils.py", line 147, in git_fix_workspace
run(f'"{git}" -C "{dir}" fetch --refetch --no-auto-gc', f"Fetching all contents for {name}", f"Couldn't fetch {name}", live=True)
File "/content/drive/MyDrive/install/modules/launch_utils.py", line 115, in run
raise RuntimeError("\n".join(error_bits))
RuntimeError: Couldn't fetch K-diffusion.
Command: "git" -C "/content/drive/MyDrive/install/repositories/k-diffusion" fetch --refetch --no-auto-gc
Error code: 129

선생님이 제공해주는 스테이블 디퓨전 (ChilloutMix)이 8월인가까지는 잘 이미지 생성 되었습니다.

그런데 요즘 어떤 것(설치버전도, 다양한 버전)을 사용해도 코랩, 구글드라이버를 활용해서 실행하다.

중간에 오류가 뜨고 스테이블 디퓨전 화면 링크가 생성되지 않습니다.

특정 옵션설정 없이도 되었었는데.. 안되는 이유를 모르겠습니다.

아래는 3월버전(stable) | 설치버전(install) | 최신(nightly) | Deforum전용 모두 동일하게 아래와 같은 에러가 발생합니다.

조치방법이나 해결책 부탁드립니다.

aunching Web UI with arguments: --xformers --no-half-vae --theme dark --ngrok 2NvULDYlp2dVAVT4r7MGemGr9aD_7rcb542dTsbjAdtuTVT8a
2023-11-09 15:14:42.439077: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-09 15:14:42.439809: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-09 15:14:42.439868: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-11-09 15:14:42.454944: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-11-09 15:14:44.794221: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Traceback (most recent call last):
File "/content/ui/launch.py", line 357, in
start()
File "/content/ui/launch.py", line 347, in start
import webui
File "/content/ui/webui.py", line 25, in
import gradio
File "/usr/local/lib/python3.10/dist-packages/gradio/init.py", line 3, in
import gradio.components as components
File "/usr/local/lib/python3.10/dist-packages/gradio/components.py", line 32, in
from gradio import media_data, processing_utils, utils
File "/usr/local/lib/python3.10/dist-packages/gradio/processing_utils.py", line 25, in
from gradio import utils
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 555, in
class AsyncRequest:
File "/usr/local/lib/python3.10/dist-packages/gradio/utils.py", line 575, in AsyncRequest
client = httpx.AsyncClient()
File "/usr/local/lib/python3.10/dist-packages/httpx/_client.py", line 1397, in init
self._transport = self._init_transport(
File "/usr/local/lib/python3.10/dist-packages/httpx/_client.py", line 1445, in _init_transport
return AsyncHTTPTransport(
File "/usr/local/lib/python3.10/dist-packages/httpx/_transports/default.py", line 275, in init
self._pool = httpcore.AsyncConnectionPool(

--- 아래와 같은 에러가 뜨면서 더이상 진행되지 않습니다.----
TypeError: AsyncConnectionPool.init() got an unexpected keyword argument 'socket_options'