Hello! This is San AI from "San AI Lab." It's a guide that will explore the mysterious and interesting worlds of Generative AI with you. This channel provides in-depth information about Generative AI technology, and guides on how to utilize the latest AI tools, especially Stable Diffusion. This section covers a variety of topics from the basics of AI technology to real-life problem solving. We'll learn how to use Stable Diffusion to generate amazing images, the process of training AI models, and how these technologies can revolutionize our daily lives and work. If you're catching up with the latest Generative AI trends and looking for practical Stable Diffusion tutorials, you're at the right place. "San AI Lab" is a space for tech enthusiasts, designers, developers, and all creative people. Join us to explore the infinite possibilities of Generative AI. Don't miss out on new discoveries and learning opportunities by subscribing and turning on notifications!
인풋 모델이라는게 inpaint 모델을 말씀 하시는 걸까요??? 기본 모델도 인페인트 가능하긴한데요. 색감등 보다 유사하게 해야할때 civitai 에서 인페인트 모델을 받으셔서 사용해보세요~ 예전에는 확실히 구분 했었는데 요즘 모델들은 vae 도 같이 포함하는 경우도 많아서 생성 해보시고 안되실때 혹은 뿌옇게 나올때 써보세요~!!
Have you tried demo? I haven't used it a lot since it's been released, but I liked the quality. If it's fast, there's no reason not to use it. Thank you.
@@sanai_labs Yes. It blew my mind it's even better than SDXL and has good understanding and also no micro flaws in the image and has understanding of many concepts like FLAX And all that in a small size it's a super model
안녕하세요, 사나이님! # ComfyUI Error Report ## Error Details - **Node Type:** AV_ControlNetPreprocessor - **Exception Type:** IndexError - **Exception Message:** list index out of range 오류가 생기는데, 해결 방법이 없을까요?ㅠ 사나인님의 apply controlnet은 왼쪽에 positive만 연결할 수 있게 되어 있는데, 제거는 negative도 연결을 해야하고, 오른쪽에는 컨디셔닝이 없고, positive와 negative로 되어 있어요. 혹시 이것 때문일까요?
앞선 댓글과 같이 파이썬 위치를 찾지 못해서 ___________________________________________________________________________________________ @echo off set PYTHON="C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\venv\Scripts\python.exe" set GIT= set VENV_DIR= set COMMANDLINE_ARGS= git reset --hard 29be1da7cf2b5dccfc70fbdd33eb35c56a31ffb7 @REM Uncomment following code to reference an existing A1111 checkout. @REM set A1111_HOME=Your A1111 checkout dir @REM @REM set VENV_DIR=%A1111_HOME%/venv @REM set COMMANDLINE_ARGS=%COMMANDLINE_ARGS% ^ @REM --ckpt-dir %A1111_HOME%/models/Stable-diffusion ^ @REM --hypernetwork-dir %A1111_HOME%/models/hypernetworks ^ @REM --embeddings-dir %A1111_HOME%/embeddings ^ @REM --lora-dir %A1111_HOME%/models/Lora call webui.bat ___________________________________________________________________________________________ 으로 파이썬 위치를 지정해서 다시한번 실행을 해보았는데요. ___________________________________________________________________________________________ venv "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\venv\Scripts\Python.exe" Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)] Version: f2.0.1v1.10.1-1.10.1 Commit hash: <none> Couldn't determine assets's hash: 6f7db241d2f8ba7457bac5ca9753331f0c266917, attempting autofix... Fetching all contents for assets '"git"'은(는) 내부 또는 외부 명령, 실행할 수 있는 프로그램, 또는 배치 파일이 아닙니다. Traceback (most recent call last): File "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\launch.py", line 54, in <module> main() File "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\launch.py", line 42, in main prepare_environment() File "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\modules\launch_utils.py", line 462, in prepare_environment git_clone(assets_repo, repo_dir('stable-diffusion-webui-assets'), "assets", assets_commit_hash) File "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\modules\launch_utils.py", line 187, in git_clone current_hash = run_git(dir, name, 'rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}", live=False).strip() File "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\modules\launch_utils.py", line 175, in run_git git_fix_workspace(dir, name) File "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\modules\launch_utils.py", line 162, 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 "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\modules\launch_utils.py", line 125, in run raise RuntimeError(" ".join(error_bits)) RuntimeError: Couldn't fetch assets. Command: "git" -C "C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge epositories\stable-diffusion-webui-assets" fetch --refetch --no-auto-gc Error code: 1 계속하려면 아무 키나 누르십시오 . . . ___________________________________________________________________________________________ 으로 오류가 나오고 있습니다. git 파일을 지정해야 하는데 git 파일은 또 어떻게 찾아야 할지 여쭤봐도 괜찮으실까요? 저는 스테빌리티 매트릭스 통해서 설치를 했는데 왜 과정이 다를까요?? 파이썬 설치 위치도 ""C:\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI Forge\venv\Scripts\Python.exe" 이면 스테빌리티 매트릭스를 통해서 설치한게 맞을텐데요
안녕하세요 항상 좋은 자료 감사드립니다. 혹시 reactor 설치할때 install.bat를 실행시키면 python: can't open file 'C:\\Users\\master\\AppData\\Roaming\\StabilityMatrix\\Packages\\ComfyUI\\venv\\Scripts\\install.py': [Errno 2] No such file or directory Done 계속하려면 아무 키나 누르십시오 . . . 이러면서 설치가 안되는데 해결방법 있을까요?
이건 모델 자체문제에요. 768 모델은 공식적으로 1280x768만 지원, 384 모델은 640x384만 지원합니다. 세로 이미지는 아직 안되요. 다른 해상도는 어느 정도 작동하는 듯하지만 품질이 훨씬 안좋아요. 대신 곧 pyramid flow 에서 새로 학습해서 모델이 나올 예정입니다. 현재 학습중이고요. 새로 모델 나오면 인물도 어느정도 나올 예정이라 하네요.
안녕하세요! 매트릭스를 실행하면 ModuleNotFoundError: No module named 'insightface.app' 하고 ModuleNotFoundError: No module named 'utils.transforms' 뜹니다. 왜 그럴까요? 답답해서 문의드립니다. 해결방법 부탁드립니다. 감사합니다.
이미지를 비디오로 변경하는 예제에 화면비율이 틀려서인지 다음처럼나오는데요. 예제는 1280* 768인데 제가 세로로 630*1120으로 바꿔서 그럴까요? ------------------------------------------<에러내용>--------------------- PyramidFlowSampler The size of tensor a (19) must match the size of tensor b (18) at non-singleton dimension 4 # ComfyUI Error Report ## Error Details - **Node Type:** PyramidFlowSampler - **Exception Type:** RuntimeError - **Exception Message:** The size of tensor a (19) must match the size of tensor b (18) at non-singleton dimension 4 ## Stack Trace ``` File "C:\comfyui ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 323, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\comfyui ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 198, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\comfyui ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "C:\comfyui ew_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 158, in process_inputs
