Downloads · 30 days
6
10% of all-time downloads
conanco/flux-kiki-lora
flux-kiki-lora is a text-to-image model from conanco. Use it when you need an image from a text prompt. It is set up for diffusers.
Downloads · 30 days
6
10% of all-time downloads
All-time downloads
60
Public
Repo size
94.4 MB
Likes
0
Public
Click a slice to open those files.
.safetensors89.7 MB · 95%
From the Hugging Face model README
A text2img styled lora weight fine-tuned on FLUX.1-dev, for my favorite Ghibli Studio animation Kiki's delivery service.
import torch
from diffusers import AutoPipelineForText2Image
base_model = "black-forest-labs/FLUX.1-dev"
pipeline = AutoPipelineForText2Image.from_pretrained(base_model, torch_dtype=torch.bfloat16).to("cuda")
repo_id = "conanco/flux-kiki-lora"
weight_name = "flux-kiki-lora.safetensors"
pipeline.load_lora_weights(repo_id, weight_name=weight_name)
generator = torch.Generator(device="cuda").manual_seed(1)
prompt = "A kikisdeliveryservice style image of a smiling girl with red bow on hair and holding a sign that says hello world."
image = pipeline(prompt, num_inference_steps=50, generator=generator).images[0]
image.save("output.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers.
You should use kikisdeliveryservice style to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.