|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
- Photonegative Refractographs |
|
widget: |
|
- text: >- |
|
Captured in a low-angle, eye-level perspective, a black and white cat stands |
|
against a stark black backdrop. The cats fur is a mix of black, white, and |
|
gray, creating a stark contrast against the dark background. The black cats |
|
face is adorned with a white line, adding a pop of color to the otherwise |
|
monochromatic image. The tail of the cat is draped over its body, adding |
|
depth to the composition. |
|
output: |
|
url: images/GB4.png |
|
- text: >- |
|
Glowing body, A close-up of a black birds head and neck is seen in a stark |
|
white lighted photograph. The birds beak is pointed towards the right side |
|
of the frame, and its eye is visible in the center of the image. The |
|
background is completely black, creating a stark contrast to the birds body |
|
and head. |
|
output: |
|
url: images/GB5.png |
|
- text: >- |
|
Glowing Body, a vibrant black-haired man stands against a dark backdrop, |
|
adorned with a glowing heart-shaped light-up shirt. The mans face is adorned |
|
with white paint, adding a pop of color to the otherwise monochromatic |
|
scene. His hair is short, cascading down to his forehead, framing his face. |
|
His eyes are covered in white paint. His lips are slightly parted, as if he |
|
is looking down at the heart. His arms are stretched out in front of him, |
|
adding depth to the composition. The heart-like shape of the shirt is |
|
glowing, creating a stark contrast against the dark backdrop. |
|
output: |
|
url: images/GB3.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Glowing Body |
|
license: creativeml-openrail-m |
|
--- |
|
# Glowing-Body-Flux-LoRA |
|
|
|
<Gallery /> |
|
|
|
- Hosted Here🧨: https://huggingface.co./spaces/prithivMLmods/FLUX-LoRA-DLC |
|
|
|
**The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.** |
|
|
|
## Model description |
|
|
|
**prithivMLmods/Glowing-Body-Flux-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 | 25 & 3.1K| |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 22 [ Hi-RES ] |
|
|
|
## Best Dimensions |
|
|
|
- 1024 x 1024 (Default) |
|
|
|
## 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 = "prithivMLmods/Glowing-Body-Flux-LoRA" |
|
trigger_word = "Glowing Body" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Data source |
|
|
|
- https://freeflo.ai/ |
|
|
|
|
|
## Trigger words |
|
|
|
You should use `Glowing Body` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Glowing-Body-Flux-LoRA/tree/main) them in the Files & versions tab. |
