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("ikmalsaid/studio-ghibli-flux-dev-lora")
prompt = "a happy man in the style of gh1bli <lora:gh1bli-style:1>"
image = pipe(prompt).images[0]Studio Ghibli - Flux.1 [Dev] LORA
- Prompt
- a happy man in the style of gh1bli <lora:gh1bli-style:1>
- Prompt
- luxurious and fabulous h0ekstra posing stand in the style of gh1bli <lora:gh1bli-style:1.5> <lora:h0ekstra-lora-dev2pro:0.8>
- Prompt
- in the style of gh1bli a car. <lora:gh1bli-style:1>
- Prompt
- in the style of gh1bli a woman wearing wedding gown <lora:gh1bli-style:1.2>
- Prompt
- in the style of gh1bli a policewoman escorting a girl <lora:gh1bli-style:1.2>
- Prompt
- in the style of gh1bli woman wearing a french maid outfit holding a tray of fruits <lora:gh1bli-style:1.2>
Model description
A magnificent anime film art style LORA trained on Flux.1 [Dev] (Dev2Pro version). Any constructive feedback and suggestions are very much appreciated. Thank you for your support!
Trigger words
You should use in the style of gh1bli 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
- 17
Model tree for ikmalsaid/studio-ghibli-flux-dev-lora
Base model
black-forest-labs/FLUX.1-dev