sdxl-color LoRA by fofr
An SDXL fine-tune for solid color images
Inference with Replicate API
Grab your replicate token here
pip install replicate
export REPLICATE_API_TOKEN=r8_*************************************
import replicate
output = replicate.run(
"sdxl-color@sha256:454561fe18009840dd04e07df5012cdad42b8dfe87e6814c9f8e3e323d9bcfbe",
input={"prompt": "A TOK red living room, sofa"}
)
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 <s0><s1>
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 cog_sdxl.dataset_and_utils import TokenEmbeddingsHandler
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("fofr/sdxl-color", weight_name="lora.safetensors")
text_encoders = [pipe.text_encoder, pipe.text_encoder_2]
tokenizers = [pipe.tokenizer, pipe.tokenizer_2]
embedding_path = hf_hub_download(repo_id="fofr/sdxl-color", filename="embeddings.pti", repo_type="model")
embhandler = TokenEmbeddingsHandler(text_encoders, tokenizers)
embhandler.load_embeddings(embedding_path)
prompt="A <s0><s1> red living room, sofa"
images = pipe(
prompt,
cross_attention_kwargs={"scale": 0.8},
).images
#your output image
images[0]
- Downloads last month
- 15
Model tree for fofr/sdxl-color
Base model
stabilityai/stable-diffusion-xl-base-1.0
Adapter
this model