FLUX AestheticAnime

🚀 FLUX-AestheticAnime

This is a LoRA model trained on the unique style and aesthetic of Ghibli retro anime, enabling text - to - image generation with a distinct anime style.

🚀 Quick Start

This model can generate images based on text prompts. You can use it with the diffusers library. Here is a basic example:

from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('dataautogpt3/FLUX-AestheticAnime', weight_name='Flux_1_Dev_LoRA_AestheticAnime.safetensors')
image = pipeline('anime girl').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers.

✨ Features

• Unique Aesthetic: Trained on the unique style and aesthetic of Ghibli retro anime.
• 16 Rank LoRA: Utilizes a 16 - rank LoRA structure.
• No Trigger Word: There is no need for a trigger word to generate images.

💻 Usage Examples

Basic Usage

from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('dataautogpt3/FLUX-AestheticAnime', weight_name='Flux_1_Dev_LoRA_AestheticAnime.safetensors')
image = pipeline('anime girl').images[0]

📚 Documentation

Model description

Lora trained on the unique style and aesthetic of ghibli retro anime. 16 rank lora.

Trigger words

No trigger word

📄 License

Please adhere to the licensing terms as described here.