Downloads · 30 days
20
69% of all-time downloads
chrisserycher/docmartens23
docmartens23 is a text-to-image model from chrisserycher. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
20
69% of all-time downloads
All-time downloads
29
Public
Repo size
779 MB
Likes
0
Public
Click a slice to open those files.
.safetensors576 MB · 59%
From the Hugging Face model README
A DreamBooth-LoRA for Krea 2, trained on Krea 2 RAW and shown on Krea 2 Turbo. The samples below were generated with this LoRA on Turbo (8 steps).
Use the token docmartens23 to invoke the concept.

"A futuristic cyberpunk street market in Neo-Tokyo, neon rain reflecting off a pair of scuffed docmartens23 boots stepping through a glowing puddle."

"An ethereal, sun-drenched Victorian greenhouse filled with overgrown ferns and white lilies, featuring a single pair of polished docmartens23 resting on a marble floor."

"A gritty, high-contrast black and white shot of a 1970s punk rock basement show, focusing on a musician's feet wearing chunky docmartens23 amidst a sea of amplifier cables."
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("chrisserycher/docmartens23")
image = pipe("A futuristic cyberpunk street market in Neo-Tokyo, neon rain reflecting off a pair of scuffed docmartens23 boots stepping through a glowing puddle.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")