|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
widget: |
|
- text: 'Golden Dust, A close-up shot of a golden retriever dogs face is seen in a vibrant orange hue. The dogs fur is a mix of brown and white, and the dogs nose is a darker shade of brown. Its eyes are a deep brown, and its ears are a lighter brown. The background is blurred, and there are small orange dots dotting the fur around its neck, adding a festive touch to the scene.' |
|
output: |
|
url: images/GD1.png |
|
- text: 'Golden Dust, A close-up view of a cheeseburger on a table. The hamburger is made up of a dark brown bun, with a layer of melted cheese on top of it. The cheese is a bright yellow, and there is a red sauce dripping from the bun. The bun is adorned with sesame seeds, adding a touch of sparkle to the scene. The table under the hamburger, is a dark wooden table, and the lighting is subdued, creating a stark contrast to the burger.' |
|
output: |
|
url: images/GD2.png |
|
- text: 'Golden Dust, A close-up eye-level shot of a womans face, adorned with sparkles of golden light. The womans eyes are adorned with green eyes, adding a pop of color to the scene. Her eyebrows are a darker shade of brown, while her eyelashes are a lighter shade of green. Her lips are a vibrant shade of red, her nose is adorned with a light pink tint. Her hair is a dark brown, wavy, and she has long bangs. The background is dark, creating a stark contrast to her face.' |
|
output: |
|
url: images/GD3.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Golden Dust |
|
license: creativeml-openrail-m |
|
--- |
|
# Golden-Dust-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/Golden-Dust-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 & 2500| |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 17 [ Hi-RES ] |
|
|
|
## Other Sample Image |
|
|
|
 |
|
|
|
## 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/Golden-Dust-Flux-LoRA" |
|
trigger_word = "Golden Dust" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Data source |
|
|
|
- https://freeflo.ai/ |
|
|
|
## Trigger words |
|
|
|
You should use `Golden Dust` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Golden-Dust-Flux-LoRA/tree/main) them in the Files & versions tab. |
|
|
