Instructions to use liming518/krea2pulledout with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use liming518/krea2pulledout with Diffusers:
pip install -U diffusers transformers accelerate
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("liming518/krea2pulledout") prompt = "Cropped example picture from the creator" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-to-image
|
| 4 |
+
- lora
|
| 5 |
+
- diffusers
|
| 6 |
+
- template:diffusion-lora
|
| 7 |
+
widget:
|
| 8 |
+
- output:
|
| 9 |
+
url: >-
|
| 10 |
+
images/_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__1686863737(1).png
|
| 11 |
+
text: >-
|
| 12 |
+
A photo-realistic photograph of a adult woman with long blonde hair, wearing
|
| 13 |
+
a brown parka with a fur-lined hood. the woman, who appears to be in her
|
| 14 |
+
late s or early twenties, has a serious expression and is resting her chin
|
| 15 |
+
on her hand. she is looking directly at the camera with her blue eyes. her
|
| 16 |
+
blonde hair is styled in loose waves and falls down her back. she is wearing
|
| 17 |
+
a beige parka with a fur-lined hood, which is slightly open, revealing her
|
| 18 |
+
bare shoulders. the parka has a zipper closure and two pockets on the front.
|
| 19 |
+
the background is blurred, but it appears to be an outdoor setting with
|
| 20 |
+
trees and a cloudy sky. the image has a sepia tone, giving it a melancholic
|
| 21 |
+
atmosphere. the overall mood of the image is somber and contemplative.,,
|
| 22 |
+
- output:
|
| 23 |
+
url: >-
|
| 24 |
+
images/卡丹_史诗级电影感_高细节写实风格_黄金时段光照_中景镜头_一位十八岁的草原部落公主_身姿纤瘦_拥有令人屏息的东方古典美和野性气息_她_1686863737.png
|
| 25 |
+
text: >-
|
| 26 |
+
A cinematic, hyper-realistic medium shot of a funny meme scene captured as a
|
| 27 |
+
low-quality smartphone portrait. In the close foreground drunk Chihuahua
|
| 28 |
+
holds its out to take a candid selfie, looking directly at the camera with a
|
| 29 |
+
comical, strong side-eye expression and its tongue hanging out. the
|
| 30 |
+
protruding tongue hangs out of the mouth vertically downwards without
|
| 31 |
+
control. Sitting upright against a tiled wall directly behind the dog is a
|
| 32 |
+
large, relaxed crocodile, resting in a human-like sitting position. On the
|
| 33 |
+
tiled floor next to them sits a small glass mug filled with dark tea and a
|
| 34 |
+
generic red Marlboro cigarette pack. The casual indoor scene features flat
|
| 35 |
+
smartphone flash lighting, slight motion blur, compressed image artifacts,
|
| 36 |
+
and an authentic, grainy low-resolution digital photo aesthetic.
|
| 37 |
+
- output:
|
| 38 |
+
url: >-
|
| 39 |
+
images/_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__1686863737.png
|
| 40 |
+
text: >-
|
| 41 |
+
A photo-realistic shoot from a frontal camera angle about a adult woman
|
| 42 |
+
wearing a green crocheted crop top and light blue jeans. the image also
|
| 43 |
+
shows a woman standing in the middle of the image. on the middle of the
|
| 44 |
+
image, a 17-18 year old woman with long black hair, wearing a green crochet
|
| 45 |
+
crop top that reveals her medium-sized breasts and a pair of light blue
|
| 46 |
+
jeans. she appears to be smiling and looking directly at the camera. her
|
| 47 |
+
hair is styled in two braids, and she has brown eyes. she is wearing a gold
|
| 48 |
+
necklace with a pendant and several bracelets on her wrists. the room is
|
| 49 |
+
dimly lit, with a bed and some objects in the background. the lighting is
|
| 50 |
+
soft and natural, highlighting her curves and the texture of the crocheted
|
| 51 |
+
fabric.,,
|
| 52 |
+
- output:
|
| 53 |
+
url: >-
|
| 54 |
+
images/_subject__an__she_has_a_soft_oval_shaped_face_and_long_eyelashes__she_has_black_hair__very_long_hair__action__she_is_standing_straight_up__contrapposto_with_more_weight_on_one_foot__pro_3265296889.png
|
| 55 |
+
text: >-
|
| 56 |
+
Subject: An, she has a soft oval shaped face and long eyelashes, She has
|
| 57 |
+
black hair, very long hair.
|
| 58 |
+
- output:
|
| 59 |
+
url: >-
|
| 60 |
+
images/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_1960717478.png
|
| 61 |
+
text: >-
|
| 62 |
+
A cinematic, hyper-realistic medium shot of a funny meme scene captured as a
|
| 63 |
+
low-quality smartphone portrait. In the close foreground, a light-brown
|
| 64 |
+
mixed-breed dog holds its paw out to take a candid selfie, looking directly
|
| 65 |
+
at the camera with a comical, side-eye expression. Sitting upright against a
|
| 66 |
+
tiled wall directly behind the dog is a large, relaxed crocodile, resting in
|
| 67 |
+
a human-like sitting position. On the tiled floor next to them sits a small
|
| 68 |
+
glass mug filled with dark tea and a generic red cigarette pack. The casual
|
| 69 |
+
indoor scene features flat smartphone flash lighting, slight motion blur,
|
| 70 |
+
compressed image artifacts, and an authentic, grainy low-resolution digital
|
| 71 |
+
photo aesthetic.
|
| 72 |
+
base_model: krea/Krea-2-Turbo
|
| 73 |
+
instance_prompt: null
|
| 74 |
+
|
| 75 |
+
---
|
| 76 |
+
# Extracted Loras from Krea 2 (Turbo) finetunes
|
| 77 |
+
|
| 78 |
+
<Gallery />
|
| 79 |
+
|
| 80 |
+
## Model description
|
| 81 |
+
|
| 82 |
+
These LoRAs were extracted from fine-tuned checkpoints. I did this primarily for myself because LoRAs are easier to work with: they can be mixed in real time and assigned different weights/strengths. This also saves space on your local computer. They work well at 100–150% strength. Choose a rank according to your taste and your hardware capabilities (the lower the rank, the less memory you need). However, some of my test generations showed that a lower rank can sometimes be preferable: it does not cause artifacts, and the result is closer to the reference image generated using the checkpoint from which the LoRA was extracted.
|
| 83 |
+
|
| 84 |
+
A lot of time, electricity, and compute went into this on my small and not particularly powerful Mac Mini M4. But it was an interesting research project.
|
| 85 |
+
|
| 86 |
+
## Download model
|
| 87 |
+
|
| 88 |
+
|
| 89 |
+
[Download](/Omnico/Krea2_turbo_diff_loras/tree/main) them in the Files & versions tab.
|