OneTrainer
OneTrainer copied to clipboard
Nerogar
OneTrainer is a one-stop solution for all your stable diffusion training needs.
### What happened?  ### What did you expect would happen? That the image is not zoomed in ### Relevant log output ```shell N/A ``` ### Output of `pip freeze`...
### What happened? Training inpainting uses GenerateMaskedConditioningImage generating the conditioning image with the inpainting mask. The inpainting training typically works like this: 1. The model is given the masked image...
### What happened? All SDXL LORAs trained in OneTrainer over the last 60 days are unable to be merged, together, or directly with a checkpoint, using either Kohya_ss or Supermerger....
### What happened? Any time I attempt to test LARS or LAMB the error happens. ### What did you expect would happen? No errors ### Relevant log output ```shell step:...
I trained some FineTune (Stable Cascade) in OneTrainer. Samples looks ok. But I got 2 files stage_c.safetensors 7GB text_encoder.safetensors 1.5GB Comfyui workflows need 9GB single file. Please tell how to...
Hello, using OneTrainer on Windows 11. I remote into my workstation from a laptop. I was running a fine tune job overnight, and in the morning the UI was in...
### Describe your use-case. I recently started using Florence-2 (https://huggingface.co/microsoft/Florence-2-base) in ComfyUI to caption images and was blown away by the lightweight model's speed and accuracy and versatility. It is...
### What happened? I developped a tool to easily merge checkpoints together and I've noticed that OneTrainer is generating checkpoints a little bit bigger than the one generated in the...
### What happened? gits/OneTrainer/venv/lib/python3.10/site-packages/torch/autograd/graph.py:744: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.) return Variable._execution_engine.run_backward( # Calls into the C++ engine to run...
### Describe your use-case. There are multiple simple models used in this repository: Blip, Clip and WD-taggers. However, when it comes to detailed description, they are all dwarfed by modern...
