Downloads · 30 days
34
8% of all-time downloads
Tyl3rDrden/trained-flux-dev-dreambooth-Jonathan_Pure_TEXTUAL_INVERSION
trained-flux-dev-dreambooth-Jonathan_Pure_TEXTUAL_INVERSION is a text-to-image model from Tyl3rDrden. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
34
8% of all-time downloads
All-time downloads
403
Public
Repo size
7.7 GB
Likes
0
Public
Click a slice to open those files.
.bin7.4 GB · 97%
From the Hugging Face model README
These are Tyl3rDrden/trained-flux-dev-dreambooth-Jonathan_Pure_TEXTUAL_INVERSION DreamBooth LoRA weights for black-forest-labs/FLUX.1-dev.
The weights were trained using DreamBooth with the Flux diffusers trainer.
Was LoRA for the text encoder enabled? False.
Pivotal tuning was enabled: True.
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
to trigger concept `<sksman>` → use `<s0><s1><s2><s3><s4><s5>` in your prompt
Download the *.safetensors LoRA in the Files & versions tab.
from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('Tyl3rDrden/trained-flux-dev-dreambooth-Jonathan_Pure_TEXTUAL_INVERSION', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='Tyl3rDrden/trained-flux-dev-dreambooth-Jonathan_Pure_TEXTUAL_INVERSION', filename='trained-flux-dev-dreambooth-Jonathan_Pure_TEXTUAL_INVERSION_emb.safetensors', repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>", "<s2>", "<s3>", "<s4>", "<s5>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["t5"], token=["<s0>", "<s1>", "<s2>", "<s3>", "<s4>", "<s5>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
image = pipeline('A photo of <s0><s1><s2><s3><s4><s5> in a bucket').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers
Please adhere to the licensing terms as described here.
# TODO: add an example code snippet for running this diffusion pipeline
[TODO: provide examples of latent issues and potential remediations]
[TODO: describe the data used to train the model]