vikas784

Results 5 issues of vikas784

## 🛠️ SD3 FineTuning Setup (Complete Guide) ### 1. ✅ Training Command ```bash accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 sd3_train.py \ --save_model_as safetensors \ --train_data_dir "/workspace/sdxl/sd3/sd-scripts/exp_1_sd_3_training_Data" \ --in_json "/workspace/sdxl/sd3/sd-scripts/exp_1_sd_3_training_Data/meta_lat.json" \...

I am currently working on full SDXL fine-tuning but have encountered challenges in finding the best code due to conflicting information from various sources. Previously, I used the GitHub repository...

![Image](https://github.com/user-attachments/assets/57b88d56-0d50-4651-8d80-f53d6a74872b) Actuallly i made this latents using code provided in sdxl prepare_bucket_latents.py file, Please anyone help me in solving this error

### 🚨 Issue: LoRA Not Updating Custom Fine-Tuned SDXL Model in SPO Training I am training a model in two stages: 1️⃣ **Stage 1 (Step-Aware Preference Model Training)** - Trained...

So actually i am trying to train the model on my own data and i have own finetuned sdxk model , so i m confused on two things , First...