---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: 'Anime Xmas: A cute anime boy with messy dark brown hair and glasses, wearing a green sweater with a reindeer pattern. He is sitting under a decorated Christmas tree, wrapping a gift with golden ribbon. A small white cat wearing a tiny red Santa hat is curled up beside him, adding a playful touch to the scene.'
  output:
    url: images/4.png
- text: 'Anime Xmas: A cheerful anime girl with short silver hair and blue eyes, wearing a cozy white sweater with red and green Christmas patterns. She has a red Santa hat tilted to the side and is holding a steaming mug of hot cocoa topped with marshmallows. In the background, a fireplace decorated with stockings and fairy lights adds a warm, festive atmosphere.'
  output:
    url: images/5.png
- text: 'Anime Xmas: A cozy anime family portrait of a mother, father, and two kids sitting by the Christmas tree. The mother wears a red cardigan and white scarf, while the father has a green sweater with snowmen on it. The kids, wearing matching reindeer pajamas, excitedly hold a shiny gold star ready to place on top of the tree.'
  output:
    url: images/6.png
- text: 'Anime Xmas, An animated image of a girl with long blonde hair and brown eyes. She is dressed in a red and white Christmas outfit, with a white Santa hat on her head. The girl is holding a gift in her right hand, and her left hand is wrapped in a white napkin. The background is a bright white, creating a stark contrast to the girls outfit.'
  output:
    url: images/1.png
- text: 'Anime Xmas, A cartoon drawing of Santa Claus with long white hair and a red Santa hat. The Santa Claus is wearing a red dress with a white scarf around its neck. There is a candy cane on the right side of the Santa Clauss chest. There are three white balls hanging from the scarf. A red and white candy cane is hanging from a brown door. A yellow star is hanging on the door.'
  output:
    url: images/2.png
- text: 'Anime Xmas, two cartoon characters are standing side-by-side. The character on the left is wearing a red t-shirt with white snowflakes on it, and a red Santa hat on his head. He has red eyes and a frown on his face. His eyes are squinted, and his mouth is slightly open. His head is turned to the right, and he has green eyes, a white beard, and black hair. His hat is adorned with a white fluffy pom-pom, and the cap has a white pom pom on it. His outfit is a festive red and green outfit, adorned with white fur trim. In the background, a Christmas tree can be seen, adding a festive touch to the scene.'
  output:
    url: images/3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Anime Xmas
license: creativeml-openrail-m
---
![sedgfdb.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/1fDyuXhNk3QJEHANc6b1l.png)

<Gallery />

# Model description for Flux-Anime-Xmas-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           | 27 & 3100 |
| Epoch                     | 18   | Save Every N Epochs       | 1     |

    Labeling: florence2-en(natural language & English)
    
    Total Images Used for Training : 22
    
## Best Dimensions & Inference

| **Dimensions** | **Aspect Ratio** | **Recommendation**       |
|-----------------|------------------|---------------------------|
| 1280 x 832      | 3:2              | Best                     |
| 1024 x 1024     | 1:1              | Default                  |

### Inference Range

- **Recommended Inference Steps:** 30–35

## 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-Anime-Xmas-LoRA"
trigger_word = "Anime Xmas"  
pipe.load_lora_weights(lora_repo)

device = torch.device("cuda")
pipe.to(device)
```
## Trigger words

You should use `Anime Xmas` to trigger the image generation.

## Download model

Weights for this model are available in Safetensors format.

[Download](/strangerzonehf/Flux-Anime-Xmas-LoRA/tree/main) them in the Files & versions tab.