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("HalimAlrasihi/m1st1c")
prompt = "m1st1c, a whimsical creature that resembles a mix between a kangaroo and a deer, with antlers that bloom into flowers and a tail that glows softly in the dark , in the style of m1st1c."
image = pipe(prompt).images[0]M1St1C
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use m1st1c to trigger the image generation.
Prompt Structure
m1st1c, [Prompt],in the style of m1st1c
Use it with the 🧨 diffusers library
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('HalimAlrasihi/m1st1c', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
- Downloads last month
- 5
Model tree for HalimAlrasihi/m1st1c
Base model
black-forest-labs/FLUX.1-dev