|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
- Aura++ |
|
- Aura9999 |
|
- Glow |
|
- Illusion |
|
- Render |
|
widget: |
|
- text: >- |
|
Aura 9999, a close-up of a womans face is visible. The womans eyes are a |
|
piercing yellow, while her lips are a darker shade of brown. Her hair is a |
|
mix of black and white, and she is wearing a headband that is adorned with |
|
orange lights. The background is a dark gray, and the womans head is encased |
|
in a layer of orange lights, creating a striking contrast to her face. |
|
output: |
|
url: images/A1.png |
|
- text: >- |
|
Aura 9999, a hamburger is captured in a vibrant blue-green glow. The |
|
hamburger bun is adorned with sesame seeds, adding a pop of color to the |
|
otherwise monochromatic scene. The burger is situated in the center of the |
|
frame, with a layer of lettuce surrounding it. The lettuce is a vibrant |
|
shade of green, while the tomato slices are a vibrant red. The sandwich is |
|
positioned in front of a backdrop of smoke, creating a stark contrast to the |
|
burger. The lighting is subdued in the foreground, adding depth to the |
|
composition. |
|
output: |
|
url: images/A2.png |
|
- text: >- |
|
Aura 9999, a silhouette of a mans face can be seen in front of a dark |
|
background. The mans head is facing towards the right side of the frame, and |
|
his eyes are slightly open. His hair is a mix of brown and yellow, and he |
|
has a slight smile on his face. His mouth is slightly open, and there is a |
|
line of fire behind him, adding a touch of warmth to the scene. |
|
output: |
|
url: images/A3.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Aura 9999 |
|
license: creativeml-openrail-m |
|
--- |
|
# Aura 9999 Flux LoRA |
|
|
|
<Gallery /> |
|
|
|
- Even a Hamburger Has Its Aura 🤗 |
|
|
|
- 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/Aura-9999** |
|
|
|
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 | 22 & 2390| |
|
| Epoch | 13n | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 17 [ 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/Aura-9999" |
|
trigger_word = "Aura 9999" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Trigger words |
|
|
|
You should use `Aura 9999` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
|
|
[Download](/prithivMLmods/Aura-9999/tree/main) them in the Files & versions tab. |
