|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
- Flux |
|
- Anime |
|
- Pruned |
|
widget: |
|
- text: >- |
|
Animeo, An animated animated image of a man with blonde hair and blue eyes. |
|
He is wearing a purple hoodie with a hoodie underneath. His arms are crossed |
|
over his chest and he is sitting on a black bench. Behind him is a green |
|
wall and behind the wall are a row of skyscrapers. The sky is blue with a |
|
few white clouds. |
|
output: |
|
url: images/A1.png |
|
- text: >- |
|
Animeo, An animated cartoon girl with long light blue hair, a pink tank top, |
|
and black gloves. She is holding a red and white lollipop in her right hand. |
|
The background is a dark blue. |
|
output: |
|
url: images/A3.png |
|
- text: >- |
|
Animeo, An animated image of an anime girl with long black hair and a bow on |
|
her head. She is wearing a white dress with a blue belt around her waist. |
|
The girls eyes are blue and she has a serious expression on her face. The |
|
background is a vibrant blue with white letters that spell out the word |
|
"RAIDEN". |
|
output: |
|
url: images/A4.png |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Animeo |
|
license: apache-2.0 |
|
--- |
|
 |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
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 | 35 & 4700| |
|
| Epoch | 22 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 50 [ 10@5 ] [ Hi -Res ] |
|
|
|
## Best Dimensions |
|
|
|
- 768 x 1024 (Best) |
|
- 1024 x 1024 (Default) |
|
|
|
## Setting Up |
|
```python |
|
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-Animeo-v1-LoRA" |
|
trigger_word = "Animeo" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Trigger words |
|
|
|
You should use `Animeo` to trigger the image generation. |
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/strangerzonehf/Flux-Animeo-v1-LoRA/tree/main) them in the Files & versions tab. |
