|
--- |
|
tags: |
|
- text-to-image |
|
- lora |
|
- diffusers |
|
- template:diffusion-lora |
|
widget: |
|
- text: 'Amxtoon, a woman with long brown hair and blue eyes is standing next to a anime doll with long black hair. The doll on the left is wearing a gray t-shirt with an orange and yellow sweater draped over it. The woman on the right is smiling and looking at the camera. In the background, a painting of a fire is visible on the wall.' |
|
output: |
|
url: images/am1.webp |
|
- text: 'Amxtoon, Captured in a close-up, eye-level perspective, a woman with long blonde hair, wearing a gray t-shirt, is seated at a brown wooden table with two white coffee mugs in front of her. She is smiling, with her left hand resting on her hip. Her right hand is resting on a white saucer, adding a touch of warmth to the scene. The anime womans face is adorned with blue eyes, pink ears, and a green dress adorned with a white collar. The background is blurred, suggesting a coffee shop.' |
|
output: |
|
url: images/am2.webp |
|
- text: 'Amxtoon: A woman with long, straight silver hair and violet eyes stands beside an anime doll with rainbow-colored hair and sparkly eyes. The doll on the right wears a denim jacket with patches, while the woman on the left wears a casual black turtleneck, glancing shyly at the doll. A painting of a night sky filled with stars is visible on the wall behind them.' |
|
output: |
|
url: images/am3.webp |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: Amxtoon |
|
license: creativeml-openrail-m |
|
--- |
|
# Ton618-Amxtoon-Flux-LoRA |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
**prithivMLmods/Ton618-Tarot-Cards-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 | 20 & 1.8K | |
|
| Epoch | 15 | Save Every N Epochs | 1 | |
|
|
|
Labeling: florence2-en(natural language & English) |
|
|
|
Total Images Used for Training : 15 [ Hi-RES ] |
|
|
|
## 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/Ton618-Amxtoon-Flux-LoRA" |
|
trigger_word = "Amxtoon" |
|
pipe.load_lora_weights(lora_repo) |
|
|
|
device = torch.device("cuda") |
|
pipe.to(device) |
|
``` |
|
## Concept Ideation from |
|
|
|
https://x.com/DarbyBaileyXO/status/1851388809067577805 |
|
|
|
https://x.com/MaxPanRa/status/1851385552844587200 |
|
|
|
https://x.com/aimikummd/status/1851180111648669877 |
|
|
|
Data Source Obtained / Generated from **playground.com** |
|
|
|
## Data source |
|
|
|
Playground: https://playground.com/ |
|
|
|
## Trigger words |
|
|
|
You should use `Amxtoon` to trigger the image generation. |
|
|
|
|
|
## Download model |
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
[Download](/prithivMLmods/Ton618-Amxtoon-Flux-LoRA/tree/main) them in the Files & versions tab. |
|
|
