Flux DreamBooth LoRA - cwhuh/babyface_flux_dlora_Hispanic

Model description

These are cwhuh/babyface_flux_dlora_Hispanic 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.

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 `Hispanic` → use `<s0><s1><s2><s3><s4><s5><s6><s7><s8><s9><s10><s11><s12><s13><s14><s15><s16><s17><s18><s19><s20><s21><s22><s23><s24><s25><s26><s27><s28><s29><s30><s31><s32><s33><s34><s35><s36><s37><s38><s39><s40><s41><s42><s43><s44><s45><s46><s47><s48><s49><s50><s51><s52><s53><s54><s55><s56>` in your prompt 

Download model

Download the *.safetensors LoRA in the Files & versions tab.

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("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('cwhuh/babyface_flux_dlora_Hispanic', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='cwhuh/babyface_flux_dlora_Hispanic', filename='/nas/checkpoints/sangmin/babyface_flux_dlora_Hispanic_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>", "<s6>", "<s7>", "<s8>", "<s9>", "<s10>", "<s11>", "<s12>", "<s13>", "<s14>", "<s15>", "<s16>", "<s17>", "<s18>", "<s19>", "<s20>", "<s21>", "<s22>", "<s23>", "<s24>", "<s25>", "<s26>", "<s27>", "<s28>", "<s29>", "<s30>", "<s31>", "<s32>", "<s33>", "<s34>", "<s35>", "<s36>", "<s37>", "<s38>", "<s39>", "<s40>", "<s41>", "<s42>", "<s43>", "<s44>", "<s45>", "<s46>", "<s47>", "<s48>", "<s49>", "<s50>", "<s51>", "<s52>", "<s53>", "<s54>", "<s55>", "<s56>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
            
image = pipeline('A newborn <s0><s1><s2><s3><s4><s5><s6><s7><s8><s9><s10><s11><s12><s13><s14><s15><s16><s17><s18><s19><s20><s21><s22><s23><s24><s25><s26><s27><s28><s29><s30><s31><s32><s33><s34><s35><s36><s37><s38><s39><s40><s41><s42><s43><s44><s45><s46><s47><s48><s49><s50><s51><s52><s53><s54><s55><s56> baby with a peaceful, sleeping face. The baby is wearing a white beanie and is swaddled in a white blanket. The background is a soft, neutral white, matching the original clean studio aesthetic. Ultra-realistic, highly detailed, soft lighting, professional photography.').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers

License

Please adhere to the licensing terms as described here.

Intended uses & limitations

How to use

# TODO: add an example code snippet for running this diffusion pipeline

Limitations and bias

[TODO: provide examples of latent issues and potential remediations]

Training details

[TODO: describe the data used to train the model]