SDXL LoRA DreamBooth - rourkepalmer/desma-160-2-lora

Prompt

A photo of <s0><s1> a close up of a red dahlia flower

Prompt

A photo of <s0><s1> a pink dahlia flower on a blurred leafy, flowery background

Prompt

A photo of <s0><s1> two pink dahlia flowers on a dark background

Prompt

A photo of <s0><s1> a red dahlia flower on a leafy background

Prompt

A photo of <s0><s1> a close up of a pink dahlia flower

Prompt

A photo of <s0><s1> a close up of two pink dahlia flowers on a leafy, flowery background

Prompt

A photo of <s0><s1> a side-on of a pink dahlia flower on a blurred dark background

Prompt

A photo of <s0><s1> a pink dahlia flower on a blurred leafy background

Prompt

A photo of <s0><s1> a side-on of a yellow dahlia flower with purple tips on a blurred leafy background

Prompt

A photo of <s0><s1> a pink dahlia flower on a leafy background

Prompt

A photo of <s0><s1> an orange dahlia flower on a black background

Prompt

A photo of <s0><s1> orange dahlia flower on a leafy background

Prompt

A photo of <s0><s1> a white dahlia flower with purple tips on a dark background

Prompt

A photo of <s0><s1> a red and white dahlia flower on a leafy background

Prompt

A photo of <s0><s1> a white dahlia flower with pink tips on a blurred leafy background

Prompt

A photo of <s0><s1> a white dahlia flower with a pink center on a black background

Prompt

A photo of <s0><s1> a orange dahlia flower on green background

Prompt

A photo of <s0><s1> a white dahlia flower with purple tips on a gray background

Prompt

A photo of <s0><s1> a white dahlia flower on a blurred leafy background

Prompt

A photo of <s0><s1> a red dahlia flower on a leafy, flowery background

Prompt

A photo of <s0><s1> a pink dahlia flower on a leafy, flowery background

Model description

These are rourkepalmer/desma-160-2-lora 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

• LoRA: download desma-160-2-lora.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:desma-160-2-lora:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download desma-160-2-lora_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding desma-160-2-lora_emb to your prompt. For example, A photo of desma-160-2-lora_emb (you need both the LoRA and the embeddings as they were trained together for this LoRA)

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('rourkepalmer/desma-160-2-lora', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='rourkepalmer/desma-160-2-lora', filename='desma-160-2-lora_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 photo of <s0><s1>').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 TOK → 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.