Downloads · 30 days
70
18% of all-time downloads
henrysun9074/north-atlantic-right-whale-lora-mk-1
north-atlantic-right-whale-lora-mk-1 is a text-to-image model from henrysun9074. 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
70
18% of all-time downloads
All-time downloads
387
Public
Repo size
222 MB
Likes
0
Public
Click a slice to open those files.
.safetensors186 MB · 84%
From the Hugging Face model README
north-atlantic-right-whale-lora-mk-1.safetensors here 💾.
models/Lora folder.<lora:north-atlantic-right-whale-lora-mk-1:1> to your prompt. On ComfyUI just load it as a regular LoRA.north-atlantic-right-whale-lora-mk-1_emb.safetensors here 💾.
embeddings foldernorth-atlantic-right-whale-lora-mk-1_emb to your prompt. For example, A birds-eye view drone photo of a north-atlantic-right-whale-lora-mk-1_emb swimming in the ocean near the surface
(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('henrysun9074/north-atlantic-right-whale-lora-mk-1', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='henrysun9074/north-atlantic-right-whale-lora-mk-1', filename='north-atlantic-right-whale-lora-mk-1_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 birds-eye view drone photo of a <s0><s1> swimming in the ocean near the surface').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.