thliang01's picture
Change tag
8789918 verified
metadata
tags:
  - stable-diffusion-xl
  - stable-diffusion-xl-diffusers
  - text-to-image
  - diffusers
  - template:sd-lora
  - dora
widget:
  - text: a <s0><s1> fireworks of an astronaut riding a horse
    output:
      url: image_0.png
  - text: a <s0><s1> fireworks of an astronaut riding a horse
    output:
      url: image_1.png
  - text: a <s0><s1> fireworks of an astronaut riding a horse
    output:
      url: image_2.png
  - text: a <s0><s1> fireworks of an astronaut riding a horse
    output:
      url: image_3.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: a <s0><s1> fireworks
license: openrail++

SDXL LoRA DreamBooth - thliang01/fireworks-sdxl-dora-v0-0

Prompt
a <s0><s1> fireworks of an astronaut riding a horse
Prompt
a <s0><s1> fireworks of an astronaut riding a horse
Prompt
a <s0><s1> fireworks of an astronaut riding a horse
Prompt
a <s0><s1> fireworks of an astronaut riding a horse

Model description

These are thliang01/fireworks-sdxl-dora-v0-0 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

Download model

Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
        
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('thliang01/fireworks-sdxl-dora-v0-0', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='thliang01/fireworks-sdxl-dora-v0-0', filename='fireworks-sdxl-dora-v0-0_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('a <s0><s1> fireworks of an astronaut riding a horse').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

Trigger words

To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:

to trigger concept SKS → use <s0><s1> in your prompt

Details

All Files & versions.

The weights were trained using 🧨 diffusers Advanced Dreambooth Training Script.

LoRA for the text encoder was enabled. False.

Pivotal tuning was enabled: True.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.