Downloads · 30 days
33
3% of all-time downloads
HoangDuyICT/dress-in-dsdress
dress-in-dsdress is a text-to-image model from HoangDuyICT. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as openrail++.
Downloads · 30 days
33
3% of all-time downloads
All-time downloads
958
Public
Repo size
94.3 MB
Likes
0
Public
Click a slice to open those files.
.safetensors93.3 MB · 96%
From the Hugging Face model README
dress-in-dsdress.safetensors here 💾.
models/Lora folder.<lora:dress-in-dsdress:1> to your prompt. On ComfyUI just load it as a regular LoRA.dress-in-dsdress_emb.safetensors here 💾.
embeddings folderdress-in-dsdress_emb to your prompt. For example, DSDRESS, a woman wearing a white dress with long sleeves
(you need both the LoRA and the embeddings as they were trained together for this LoRA)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('HoangDuyICT/dress-in-dsdress', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='HoangDuyICT/dress-in-dsdress', filename='dress-in-dsdress_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
image = pipeline('DSDRESS, a woman wearing a white dress with a long sleeve').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
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
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.