JPW0080
JPW0080
Example Workflow... Go to: Wherever diffusers is located/scripts Copy/Paste: convert_diffusers_to_original_stable_diffusion.py convert_original_stable_diffusion_to_diffusers.py Place the above ^ .py files in the below path: Ex: /diffusers/examples/dreambooth conda activate diffusers cd /diffusers/examples/dreambooth python convert_diffusers_to_original_stable_diffusion.py...
Indeed, perhaps provide the .sh/.bat with the COMMAND_LINE_ARGS=--disable-safe-unpickle Else, use very old webui before the command was needed... [Not recommended]
On my side, using ComfyUI-Manager, whenever Update All has been initiated, the \ComfyUI\custom_nodes\ComfyUI-InstantID\models\antelopev2 path reverts to empty dummy files that must be restored... Best to keep an copy of https://huggingface.co/DIAMONIK7777/antelopev2/tree/main...
The convoluted way that worked on my side for Win 11 offline use... Download: https://raw.githubusercontent.com/Stability-AI/generative-models/main/configs/inference/sd_xl_base.yaml Move sd_xl_base.yaml to \ComfyUI\custom_nodes\ComfyUI-InstantID Install http-server: https://learn.microsoft.com/en-us/gaming/playfab/features/authentication/platform-specific-authentication/running-an-http-server-for-testing Modify \Lib\site-packages\diffusers\pipelines\stable_diffusion\convert_from_ckpt.py Find: config_url = "https://raw.githubusercontent.com/Stability-AI/generative-models/main/configs/inference/sd_xl_base.yaml" Overwrite the...
Install Node.JS: https://nodejs.org/en/ Command Prompt: npm install -g http-server Download: https://raw.githubusercontent.com/Stability-AI/generative-models/main/configs/inference/sd_xl_base.yaml Move sd_xl_base.yaml to \ComfyUI\custom_nodes\ComfyUI-InstantID Modify \Lib\site-packages\diffusers\pipelines\stable_diffusion\convert_from_ckpt.py Find: config_url = "https://raw.githubusercontent.com/Stability-AI/generative-models/main/configs/inference/sd_xl_base.yaml" Overwrite the URL Link to "http://127.0.0.1:8080/sd_xl_base.yaml" Command Prompt: cd...
Launch webui while online, let the Dreambooth extension install it's requirements. After successful launch, Go to: Dreambooth/Create Model Create models using desired Source Checkpoints... Close it all down. Go to:...
#NOTE the below will obviously break any new requirements... Launch webui while online, let the Dreambooth extension install it's requirements. After successful launch, Go to: Dreambooth/Create Model Create models using...
The model format appears to be diffusers, ample storage space would be in order for conversions.
Unsure of the cause but 30FPS input mp4 video becomes 25FPS output mp4 video. Launch commands: python run.py --gpu-vendor nvidia --keep-frames --keep-fps python run.py --gpu-vendor nvidia Result: 25FPS video in...
It appears that anything after commit 957c5ec6ce01812d7e8a48ad4585952b59fa99bc from the next branch introduces the aforementioned 25FPS issue. Just tried commit 2beb6c23e64f79f1237cb584f4a28a1d5ae69e17 from the next branch and the output framerate issue has...