from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('pharci/akira', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]

Prompt Tutorial

To achieve the desired results with the model, formulate your prompts using the following structure:

Genre: Action, Romance, Drama, etc.
Description: What’s happening, character dynamics, etc.
Characters: Appearance, emotions, clothing, poses, interaction style, etc.
Framing: Close-up, medium shot, angle, focus details, etc.
Setting: Dark, bright, dramatic, city lights, sunset, etc.
Lighting: Simplified backgrounds, vibrant colors, sharp contours, etc.

Example Prompt

"Fantasy, A dramatic battle scene between a brave knight and a fierce dragon, The knight in shining armor, showing determination, while the dragon breathes fire, low-angle shot, set in a dark forest illuminated by firelight, vibrant colors with sharp contours."

Additional Information

This model is based on the FLUX architecture and has been adapted using LoRA weights trained on a custom dataset consisting of 500 images. The dataset focuses on specific visual styles and characteristics.

Note: This is an early test version of the model and not a final, polished release. It is still a work in progress, and future versions may include improvements and refinements.

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

pharci/anime-akira-flux

Akira

Instance Prompt

How to Use with the 🧨 Diffusers Library

Prompt Tutorial

Example Prompt

Additional Information

pharci/
anime-akira-flux