Instructions to use andynguyenhuu/andynguyen-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use andynguyenhuu/andynguyen-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("andynguyenhuu/andynguyen-lora") prompt = "A high-quality studio portrait photograph of ANDYNGUYEN, a smiling man wearing an unbuttoned tan corduroy trucker jacket over a dark navy blue crew neck t-shirt, and blue denim jeans. He has short spiked black hair and stands with his hands in his pockets. Plain light gray background, soft studio lighting, sharp focus, highly detailed, photorealistic, 8k, DSLR." image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
andynguyen
- Prompt
- A high-quality studio portrait photograph of ANDYNGUYEN, a smiling man wearing an unbuttoned tan corduroy trucker jacket over a dark navy blue crew neck t-shirt, and blue denim jeans. He has short spiked black hair and stands with his hands in his pockets. Plain light gray background, soft studio lighting, sharp focus, highly detailed, photorealistic, 8k, DSLR.
- Negative Prompt
- (worst quality, low quality:1.4), deformed, blurry, bad anatomy, bad proportions, disfigured, poorly drawn face, poorly drawn hands, extra limbs, missing limbs, closed eyes, watermark, signature, text, overexposed, harsh shadows.
- Prompt
- -
Model description
A Flux.1-dev character LoRA trained on portrait photos of Andy Nguyen (Huu Thien An Nguyen). Produces consistent facial identity across poses, lighting conditions, and outfits. Best results with chest-up or mid-torso crops at straight-on or 3/4 angles. Full-body wide shots may drift generic — use tighter framing for face fidelity.
Trigger words
You should use ANDYNGUYEN to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 3
Model tree for andynguyenhuu/andynguyen-lora
Base model
black-forest-labs/FLUX.1-dev