Image Generation
Collection
1 item • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("mihai-chindris/lora-workflow-template")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]mihai-lora-workflow (workflow-only)
This repository contains the reproducible training workflow used to run a personal SDXL LoRA pipeline on free Kaggle GPU, including checkpoint continuation, checkpoint evaluation, and LinkedIn-style gallery generation.
No personal training images, captions, generated portraits, or model checkpoints are included.
Included
- Kaggle training script (
07_kaggle/train_flux_lora.py) - Config/run automation scripts (
03_configs/*) - Evaluation script templates (
08_kaggle_eval/*) - Runbook and process notes
Excluded
- Raw/curated personal photos
- Captions tied to personal data
- Checkpoints and model weights
- Generated output galleries
- API tokens and credentials
Privacy note
If you publish similar work, keep biometric data and personal LoRA weights private unless you explicitly want public distribution.
- Downloads last month
- -