metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
Super Portrait v2, A medium-angle shot of a young man in a gray hooded
sweatshirt with the word "Ader" on the right side of the hoodie. The
hoodie has a blue stripe on the left side and a white tag with blue
letters on it. The mans head is turned to the right and he is looking to
the left. His hair is dark brown and he has a slight smile on his face. He
is wearing a blue t-shirt with a zipper on the front. The backdrop is a
vibrant blue.
output:
url: images/1.png
- text: >-
Super Portrait v2, A close-up shot of a womans face, positioned in front
of a stark white backdrop. The womans eyes are a piercing blue, her
eyebrows are a darker shade of blue, and her lips are a lighter shade of
pink. She is wearing a light green knit cap, and a matching green sweater.
Her sweater is draped over her shoulders, adding a pop of color to the
scene.
output:
url: images/2.png
- text: >-
Super Portrait v2, a close-up shot of a Asian womans face is adorned with
a gold necklace. The womans eyes are a piercing blue, and her hair is a
vibrant shade of brown. Her eyebrows are a darker shade of gray, adding a
pop of color to her face. Her lips, a lighter shade of pink, are
accentuated by a slight smile. Her hair is pulled back in a ponytail,
framing her forehead. The backdrop is a muted blue, with wavy lines adding
a touch of texture to the scene.
output:
url: images/3.png
- text: >-
Super Portrait v2, A close-up portrait of a young woman with long blonde
hair and blue eyes. She is wearing a light pink baseball cap that has a
yellow logo on the front that reads "Ori" in yellow letters. Her eyes are
a piercing blue and her eyebrows are a darker shade of brown. Her lips are
a lighter shade of pink. She has a white t-shirt with a black stripe on
the left side of the shirt. Her hair is cascading down her shoulders. The
background is a vibrant yellow.
output:
url: images/4.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Super Portrait v2
license: creativeml-openrail-m
Model description for Flux-SuperPortrait-v2-LoRA
Image Processing Parameters
Parameter | Value | Parameter | Value |
---|---|---|---|
LR Scheduler | constant | Noise Offset | 0.03 |
Optimizer | AdamW | Multires Noise Discount | 0.1 |
Network Dim | 64 | Multires Noise Iterations | 10 |
Network Alpha | 32 | Repeat & Steps | 19 & 2890 |
Epoch | 15 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 29 [ Flat 4K ]
Best Dimensions & Inference
Dimensions | Aspect Ratio | Recommendation |
---|---|---|
1280 x 832 | 3:2 | Best |
1024 x 1024 | 1:1 | Default |
Inference Range
- Recommended Inference Steps: 30–35
Setting Up
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-SuperPortrait-v2-LoRA"
trigger_word = "Super Portrait v2"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Super Portrait v2
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.