SDXL LoRA DreamBooth - computational-mama/david-and-the-forest

Prompt

<s0><s1> a drawing of two people with ink splatters on their faces

Prompt

<s0><s1> a drawing of a person with a black and white paint splatter

Prompt

<s0><s1> a drawing of a person with a black and white paint splatter

Prompt

<s0><s1> a drawing of a man with a hat and a gun

Prompt

<s0><s1> a drawing of a man with a hat and a gun

Prompt

<s0><s1> a drawing of a black and white drawing of rocks

Prompt

<s0><s1> a drawing of a black and white drawing of rocks

Prompt

<s0><s1> a drawing of a man with a face on it

Prompt

<s0><s1> a drawing of a man with a face on it

Prompt

<s0><s1> a drawing of a fish on a wall

Prompt

<s0><s1> a drawing of a person on a wall with a computer

Prompt

<s0><s1> a drawing of a man with a long body and a long head

Prompt

<s0><s1> a drawing of a dog with its tongue out

Prompt

<s0><s1> a drawing of a man with a face on it

Prompt

<s0><s1> a drawing of a man in a suit with a hat

Prompt

<s0><s1> a drawing of a man standing on a hill with a moon in the background

Prompt

<s0><s1> a drawing of a man with a face on his back

Prompt

<s0><s1> a drawing of a man with a knife and a knife

Prompt

<s0><s1> a drawing of a moon and a planet

Prompt

<s0><s1> a drawing of a spider on paper with black and white paint

Prompt

<s0><s1> a drawing of a man falling down with a black ink pen

Prompt

<s0><s1> a drawing of a black and white animal with a black and white pattern

Prompt

<s0><s1> a drawing of a group of small faces on a white wall

Model description

These are computational-mama/david-and-the-forest 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 david-and-the-forest.safetensors here 💾.
  • Place it on your models/Lora folder.
  • On AUTOMATIC1111, load the LoRA by adding <lora:david-and-the-forest:1> to your prompt. On ComfyUI just load it as a regular LoRA.
• Embeddings: download david-and-the-forest_emb.safetensors here 💾.
  • Place it on it on your embeddings folder
  • Use it by adding david-and-the-forest_emb to your prompt. (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('computational-mama/david-and-the-forest', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='computational-mama/david-and-the-forest', filename='david-and-the-forest_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('<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.