minecraft-lora LoRA by louiejancevski

None

Inference with Replicate API

Grab your replicate token here

pip install replicate
export REPLICATE_API_TOKEN=r8_*************************************

import replicate

output = replicate.run(
    "minecraft-lora@sha256:f59d2b65936fd971ea9da929a6c681664882491584364bf454cf2d464cfdd04d",
    input={"prompt": "two men minecraft_style"}
)
print(output)

You may also do inference via the API with Node.js or curl, and locally with COG and Docker, check out the Replicate API page for this model

Inference with 🧨 diffusers

Replicate SDXL LoRAs are trained with Pivotal Tuning, which combines training a concept via Dreambooth LoRA with training a new token with Textual Inversion. As diffusers doesn't yet support textual inversion for SDXL, we will use cog-sdxl TokenEmbeddingsHandler class.

The trigger tokens for your prompt will be ``

pip install diffusers transformers accelerate safetensors huggingface_hub
git clone https://github.com/replicate/cog-sdxl cog_sdxl

import torch
from huggingface_hub import hf_hub_download
from diffusers import DiffusionPipeline
from safetensors.torch import load_file
from diffusers.models import AutoencoderKL

pipe = DiffusionPipeline.from_pretrained(
        "stabilityai/stable-diffusion-xl-base-1.0",
        torch_dtype=torch.float16,
        variant="fp16",
).to("cuda")

pipe.load_lora_weights("louiejancevski/minecraft-lora", weight_name="lora.safetensors")

embedding_path = hf_hub_download(repo_id="louiejancevski/minecraft-lora", filename="embeddings.pti", repo_type="model")

state_dict = load_file(embedding_path)

pipe.load_textual_inversion(state_dict["text_encoders_0"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipe.load_textual_inversion(state_dict["text_encoders_1"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)

prompt="two men minecraft_style"
images = pipe(
    prompt,
    cross_attention_kwargs={"scale": 0.8},
).images
#your output image
images[0]