DarkViewAI

lora key not loaded

3

### Expected Behavior for it to be loaded ### Actual Behavior not loaded ### Steps to Reproduce trained a model with the text encoder on 2 h100 gpus sample images...

Trained a model/concept style on two h100 gpus experimenting with the text encoder, the lora works on comfyui but it says lora_te1.text_model.encoder.layers.8.mlp.fc1.lora_a.weight lora_te1.text_model.encoder.layers.7.mlp.fc1.lora_B.weight the images work fine when i try...

Kohya Lora not working on flux dev 1 fp8 bnb nf4 and v2

1

### Expected Behavior to work ### Actual Behavior not loaded ### Steps to Reproduce load the lora model and prompt ### Debug Logs ```powershell ``` ### Other it works fine...

Flux Text encoder loras don't work, results are either blurry or the clip is not loaded

1

### Expected Behavior to work ### Actual Behavior does not work ### Steps to Reproduce load the lora as normal and prompt for it ### Debug Logs ```powershell on the...

Flux Text encoder loras don't work, results are either blurry or the clip is not loaded

2

sample images when training it looks like subject. when trying in forge it doesn't load. i trained the clip l text encoder along with it. but doesn't work in forge...

Lora keys are unLoaded OneTrainer Flux LoRas

2

[LORA] LoRA version mismatch for KModel loras trained on onetrainer don't seem to work on forge. they get unloaded and results are quite bad. it just ignores the lora for...

lora support for one trainer loras

12

would love to use loras from one trainer on here

Kohya loras now broken after fixing one trainer lora support

6

Model loaded in 2.2s (unload existing model: 1.8s, forge model load: 0.3s). [LORA] LoRA version mismatch for KModel: D:\StabilityMatrix-win-x64\Data\Packages\stable-diffusion-webui-forge\models\Lora\Model-step00001800.safetensors Skipping unconditional conditioning when CFG = 1. Negative Prompts are ignored....

cant start training File "D:\KohyaNew\kohya_ss\kohya_gui\lora_gui.py", line 994, in train_model if max_train_steps > 0 and stop_text_encoder_training > 0: TypeError: '>' not supported between instances of 'NoneType' and 'int'

5

12:08:38-630149 INFO Dataset config TOML file used; skipping calculations for total_steps, train_batch_size, gradient_accumulation_steps, epoch, reg_factor, and max_train_steps. Traceback (most recent call last): File "D:\KohyaNew\kohya_ss\venv\lib\site-packages\gradio\queueing.py", line 536, in process_events response =...