import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("brushpenbob/flux-MidJourney")
prompt = "UNICODE\u0000\u0000a\u0000 \u0000f\u0000o\u0000x\u0000 \u0000d\u0000r\u0000e\u0000s\u0000s\u0000e\u0000d\u0000 \u0000a\u0000 \u0000a\u0000 \u0000w\u0000i\u0000z\u0000a\u0000r\u0000d\u0000,\u0000 \u0000g\u0000r\u0000e\u0000g\u0000 \u0000r\u0000u\u0000t\u0000k\u0000o\u0000w\u0000s\u0000k\u0000i\u0000"
image = pipe(prompt).images[0]FLUX MidJourney Anime
- Prompt
- UNICODEa fox dressed a a wizard, greg rutkowski
- Prompt
- ASCIIA egmid photographer on a city street with a camera, capturing a moment in motion, extremely detailed, High quality, detailed face
Model description
This is my first attempt at creating an anime style based off midjourney using flux so it might take a bit more fine tuning
https://youtu.be/QynE0UGQhRs
Trigger words
You should use egmid to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 8
Model tree for brushpenbob/flux-MidJourney
Base model
black-forest-labs/FLUX.1-dev