|
|
--- |
|
|
tags: |
|
|
- text-to-image |
|
|
- lora |
|
|
- diffusers |
|
|
- template:diffusion-lora |
|
|
widget: |
|
|
- text: gm_flux portrait smiling |
|
|
output: |
|
|
url: images/gm_train_01.jpeg |
|
|
base_model: black-forest-labs/FLUX.1-dev |
|
|
instance_prompt: gm_flux |
|
|
license: openrail |
|
|
--- |
|
|
# GiadaFlux v2 (LoRA SD-1.5) |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Model description |
|
|
|
|
|
LoRA fine-tune of **Flux 1 dev (SD-1.5)** for the custom character **Giada Moretti**. |
|
|
• 33 high-quality JPEGs – mix of close-up, half-body, full-body |
|
|
• Trained in Astria – 2 200 steps, portrait preset, face-detection ON |
|
|
• Best results with weight **0.8-1.0** and prompt token **<lora:gm_flux:0.9>** |
|
|
 |
|
|
|
|
|
|
|
|
## Trigger words |
|
|
|
|
|
You should use `gm_flux` to trigger the image generation. |
|
|
|
|
|
|
|
|
## Download model |
|
|
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
|
|
[Download](/lorenzomega/giada_flux_lora/tree/main) them in the Files & versions tab. |
|
|
|
