|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
- Red-Undersea |
|
- Red-Theme |
|
- Super-Red |
|
widget: |
|
- text: 'Red Undersea, An eye-level perspective of a 3D image of a Burger. The Burger is in the center of the image, with the Burger on the right side of the frame and the Burger on the left side. There is a blue swirl in the top left corner, and white swirls on the top right corner. There are red swirls in the bottom left corner. The background is a deep blue, and there are small white dots in the middle of the blue swirls. In the bottom right corner, there is a black surface.' |
|
output: |
|
url: images/RU1.png |
|
- text: 'Red Undersea, an illustration of a Tree in blue, in the style of glowing neon, with fish fluid formation floating around, witchcore, dark cyan and red, master of shadows, ethereal, ghostly figures ' |
|
output: |
|
url: images/RU5.png |
|
- text: 'Red Undersea, an illustration of a Candlelight in blue, in the style of glowing neon, with fish fluid formation floating around, witchcore, dark cyan and red, master of shadows, ethereal, ghostly figures ' |
|
output: |
|
url: images/RU6.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Red Undersea |
|
license: creativeml-openrail-m |
|
--- |
|
# Red-Undersea-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/Red-Undersea-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 | 23 & 2600| |
|
| Epoch | 12 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 13 [ 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/Red-Undersea-Flux-LoRA" |
|
trigger_word = "Red Undersea" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Data source |
|
|
|
- https://freeflo.ai/ |
|
|
|
## Trigger words |
|
|
|
You should use `Red Undersea` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Red-Undersea-Flux-LoRA/tree/main) them in the Files & versions tab. |
