import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("Omnico/Krea2_turbo_diff_loras")
prompt = "A photo-realistic photograph of a adult woman with long blonde hair, wearing a brown parka with a fur-lined hood. the woman, who appears to be in her late s or early twenties, has a serious expression and is resting her chin on her hand. she is looking directly at the camera with her blue eyes. her blonde hair is styled in loose waves and falls down her back. she is wearing a beige parka with a fur-lined hood, which is slightly open, revealing her bare shoulders. the parka has a zipper closure and two pockets on the front. the background is blurred, but it appears to be an outdoor setting with trees and a cloudy sky. the image has a sepia tone, giving it a melancholic atmosphere. the overall mood of the image is somber and contemplative.,,"
image = pipe(prompt).images[0]Extracted Loras from Krea 2 (Turbo) finetunes
.png)
- Prompt
- A photo-realistic photograph of a adult woman with long blonde hair, wearing a brown parka with a fur-lined hood. the woman, who appears to be in her late s or early twenties, has a serious expression and is resting her chin on her hand. she is looking directly at the camera with her blue eyes. her blonde hair is styled in loose waves and falls down her back. she is wearing a beige parka with a fur-lined hood, which is slightly open, revealing her bare shoulders. the parka has a zipper closure and two pockets on the front. the background is blurred, but it appears to be an outdoor setting with trees and a cloudy sky. the image has a sepia tone, giving it a melancholic atmosphere. the overall mood of the image is somber and contemplative.,,
- Prompt
- A cinematic, hyper-realistic medium shot of a funny meme scene captured as a low-quality smartphone portrait. In the close foreground drunk Chihuahua holds its out to take a candid selfie, looking directly at the camera with a comical, strong side-eye expression and its tongue hanging out. the protruding tongue hangs out of the mouth vertically downwards without control. Sitting upright against a tiled wall directly behind the dog is a large, relaxed crocodile, resting in a human-like sitting position. On the tiled floor next to them sits a small glass mug filled with dark tea and a generic red Marlboro cigarette pack. The casual indoor scene features flat smartphone flash lighting, slight motion blur, compressed image artifacts, and an authentic, grainy low-resolution digital photo aesthetic.
- Prompt
- A photo-realistic shoot from a frontal camera angle about a adult woman wearing a green crocheted crop top and light blue jeans. the image also shows a woman standing in the middle of the image. on the middle of the image, a 17-18 year old woman with long black hair, wearing a green crochet crop top that reveals her medium-sized breasts and a pair of light blue jeans. she appears to be smiling and looking directly at the camera. her hair is styled in two braids, and she has brown eyes. she is wearing a gold necklace with a pendant and several bracelets on her wrists. the room is dimly lit, with a bed and some objects in the background. the lighting is soft and natural, highlighting her curves and the texture of the crocheted fabric.,,
- Prompt
- Subject: An, she has a soft oval shaped face and long eyelashes, She has black hair, very long hair.
- Prompt
- A cinematic, hyper-realistic medium shot of a funny meme scene captured as a low-quality smartphone portrait. In the close foreground, a light-brown mixed-breed dog holds its paw out to take a candid selfie, looking directly at the camera with a comical, side-eye expression. Sitting upright against a tiled wall directly behind the dog is a large, relaxed crocodile, resting in a human-like sitting position. On the tiled floor next to them sits a small glass mug filled with dark tea and a generic red cigarette pack. The casual indoor scene features flat smartphone flash lighting, slight motion blur, compressed image artifacts, and an authentic, grainy low-resolution digital photo aesthetic.
Model description
Loras extracted from finely tuned checkpoints. I did it primarily for myself because it’s easier to work with Lora, including mixing them in real time and setting different weights/strengths. It also saves space on the local computer. Work well at 100-150% strength. Choose a rank according to your taste and the capabilities of your hardware (the lower the rank, the less memory you need). However, some of my test generations showed that sometimes a lower rank is preferable, does not cause artifacts and as a result is closer to the reference image generated at the checkpoint from which Lora was extracted.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 726