msrcam's picture
Upload README.md with huggingface_hub
052cce7 verified
|
Raw
History Blame Contribute Delete
495 Bytes
metadata
tags:
  - flux
  - text-encoder
  - lora
  - fine-tuned

FLUX.2 Dev Text Encoder — Fine-Tuned

Mistral 30-layer TE fine-tuned with LoRA (rank 32) on JoyCap Beta captions. Includes merged safetensors (drop-in replacement) and LoRA checkpoint.

Files

  • — merged model (35.6 GB)
  • — LoRA adapter checkpoint (529 MB)
  • — training script
  • — training log

Training

  • 3 epochs, 2,562 steps on A100 SXM4 80GB
  • Final train loss: 0.78, eval loss: 0.90
  • 13,956 JoyCap Beta captions