GGUF (quantized) models on swarmui : https://github.com/mcmonkeyprojects/SwarmUI/blob/master/docs/Mo
GGUF (quantized) models on swarmui : https://github.com/mcmonkeyprojects/SwarmUI/blob/master/docs/Model%20Support.md#gguf-quantized-models
Fyou can set swarmui model files like this - put into diffusion_models folder
F'D:/Kohya-SS-GUI/kohya_ss' is on a file system that does not record ownership
To add an exception for this directory, call:
git config --global --add safe.directory D:/Kohya-SS-GUI/kohya_ss
To add an exception for this directory, call:
git config --global --add safe.directory D:/Kohya-SS-GUI/kohya_ss
Fguys read this to learn a lot of important stuff about swarmui masking : https://github.com/mcmonkeyprojects/SwarmUI/issues/292
F
FCurrently, --highvram only affects caching of latens, and --lowvram only affects model loading. Training speed remains unchanged. - Kohya
FF
FF
Fhttps://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#cuda-12x
- onnx vs cudnn versions
Fselect cmd of kohya, hit ctrl +s to pause training, ctrl +q to continue
FTo continue DreamBooth / Fine-Tuning, give your last checkpoint as base model
To continue LoRA training, give your last LoRA checkpoint here :
To continue LoRA training, give your last LoRA checkpoint here :
Fman and woman different face classifier yolo models that can be used with swarmui : https://civitai.com/models/293448?modelVersionId=1007485
so you can give different prompt to man and woman faces automatically
so you can give different prompt to man and woman faces automatically
Faria2c -x3 -s3 aria2c -x3 -s3 <URL> -o <FILENAME>
FGGFU vs FP8 speed
Fexcellent info regarding compile issues cuda paths : https://github.com/NVlabs/nvdiffrast/issues/46#issuecomment-2458715176
F
F
F
Ffastest thinlinc client settings
Fregional prompt
FFFLUX.1 [dev] GPU performance comparison
F
Flatent upscale with flux - recommended percent 0.5-0.6
F
Fwho gets lower quality on SwarmUI uncheck this box
FNew UI feature: confused about the more complex prompt syntax inputs like Segment or Regional prompts? Be confused no more, there's now helper UIs to guide you through constructing perfect inputs every time!
FF
Fhow to load config on runpod
Fhow to generate pre-compiled wheel
Fflux image to image upscale
F
FFfor sage attention, use --use-sage-attention in the Backends tab Extra Params
Fnightly torch insall
Fexample video generation model prompt test
FFYou can pause running CMD apps : select your cmd screen and press CTRL+S it will pause. then select back and hit CTRL+Q it will resume
Fcompile
Ferror : solution :
Fremember guys when using swarmui segmentation you can change sort order
Ffrom PIL import Image, ImageOps
image = Image.open(preview_path)
image = ImageOps.exif_transpose(image)
image = Image.open(preview_path)
image = ImageOps.exif_transpose(image)
Ffix of this error (that is why follow requirements tutorial)
FComfyUI Custom Node Installation
The problem is you have to install the custom node dependencies into the venv python... Here's a command that will fix it for you:
Replace path to, with actual path
You have to use full paths to venv python and then to custom node
The problem is you have to install the custom node dependencies into the venv python... Here's a command that will fix it for you:
Replace path to, with actual path
You have to use full paths to venv python and then to custom node
FGGUF quants quality rankings list
Fframepack issue solution
Fframepack longer videos tips
