SDXL LoRA DreamBooth - revellsi/reachy-pollen

Prompt
A <s0><s1> character a robot with a camera and a microphone

Prompt
A <s0><s1> character a robot with a striped shirt and a black background

Prompt
A <s0><s1> character a man is using a laptop to play a game with a robot

Prompt
A <s0><s1> character a robot standing on a stand with a striped shirt

Prompt
A <s0><s1> character a robot with a striped shirt and a black and white striped tie

Prompt
A <s0><s1> character a robot with a striped shirt on a stand

Prompt
A <s0><s1> character a robot with a striped shirt and a hand up

Model description

These are revellsi/reachy-pollen 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 reachy-pollen.safetensors here 💾.
- Place it on your models/Lora folder.
- On AUTOMATIC1111, load the LoRA by adding <lora:reachy-pollen:1> to your prompt. On ComfyUI just load it as a regular LoRA.
Embeddings: download reachy-pollen_emb.safetensors here 💾.
- Place it on it on your embeddings folder
- Use it by adding reachy-pollen_emb to your prompt. For example, A reachy-pollen_emb character (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('revellsi/reachy-pollen', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='revellsi/reachy-pollen', filename='reachy-pollen_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> character').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.

revellsi
/

reachy-pollen