Downloads · 30 days
14
36% of all-time downloads
Ghaxalll/ghaxal-face-v2
ghaxal-face-v2 is a text-to-image model from Ghaxalll. 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
14
36% of all-time downloads
All-time downloads
39
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 ghaxal_woman to invoke the concept.

"ghaxal_woman, sitting at a desk by a window, soft afternoon light, 85mm, shallow depth of field, natural skin texture"

"ghaxal_woman, walking on a Berlin street in direct midday sun, hard shadows, candid, 35mm"

"ghaxal_woman, full body, standing against a plain turquoise tiled wall, structural black outfit, editorial fashion photograph"
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("Ghaxalll/ghaxal-face-v2")
image = pipe("ghaxal_woman, sitting at a desk by a window, soft afternoon light, 85mm, shallow depth of field, natural skin texture", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")