b / README.md

Upload README.md with huggingface_hub

7b58d6c verified 3 months ago

2 kB

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "vpx man"
widget:
- text: "A hyper-realistic portrait of a vpx man wearing iridescent neon armor, standing amidst the glowing flora of a bioluminescent alien jungle."
  output:
    url: sample_0.png
- text: "A cinematic shot of a vpx man dressed in a 1920s pinstripe suit, reading a newspaper in a rain-slicked noir city alleyway under a dim streetlamp."
  output:
    url: sample_1.png
- text: "An ethereal scene featuring a vpx man floating in a zero-gravity white void, surrounded by swirling fragments of gold leaf and floating marble sculptures."
  output:
    url: sample_2.png
---
# Krea 2 LoRA — PeterD69/b

<Gallery />

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).

## Trigger

Use the token `vpx man` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A hyper-realistic portrait of a vpx man wearing iridescent neon armor, standing amidst the glowing flora of a bioluminescent alien jungle."*

![sample](./sample_1.png)

> *"A cinematic shot of a vpx man dressed in a 1920s pinstripe suit, reading a newspaper in a rain-slicked noir city alleyway under a dim streetlamp."*

![sample](./sample_2.png)

> *"An ethereal scene featuring a vpx man floating in a zero-gravity white void, surrounded by swirling fragments of gold leaf and floating marble sculptures."*

## Use it with diffusers

```py
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("PeterD69/b")
image = pipe("A hyper-realistic portrait of a vpx man wearing iridescent neon armor, standing amidst the glowing flora of a bioluminescent alien jungle.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```

	---
	base_model: krea/Krea-2-Raw
	tags:
	- text-to-image
	- diffusers
	- lora
	- krea2
	- template:sd-lora
	license: apache-2.0
	instance_prompt: "vpx man"
	widget:
	- text: "A hyper-realistic portrait of a vpx man wearing iridescent neon armor, standing amidst the glowing flora of a bioluminescent alien jungle."
	output:
	url: sample_0.png
	- text: "A cinematic shot of a vpx man dressed in a 1920s pinstripe suit, reading a newspaper in a rain-slicked noir city alleyway under a dim streetlamp."
	output:
	url: sample_1.png
	- text: "An ethereal scene featuring a vpx man floating in a zero-gravity white void, surrounded by swirling fragments of gold leaf and floating marble sculptures."
	output:
	url: sample_2.png
	---

	# Krea 2 LoRA — PeterD69/b

	<Gallery />

	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).

	## Trigger

	Use the token `vpx man` to invoke the concept.

	## Samples

	![sample](./sample_0.png)

	> "A hyper-realistic portrait of a vpx man wearing iridescent neon armor, standing amidst the glowing flora of a bioluminescent alien jungle."

	![sample](./sample_1.png)

	> "A cinematic shot of a vpx man dressed in a 1920s pinstripe suit, reading a newspaper in a rain-slicked noir city alleyway under a dim streetlamp."

	![sample](./sample_2.png)

	> "An ethereal scene featuring a vpx man floating in a zero-gravity white void, surrounded by swirling fragments of gold leaf and floating marble sculptures."

	## Use it with diffusers

	```py
	import torch
	from diffusers import Krea2Pipeline

	pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
	pipe.load_lora_weights("PeterD69/b")
	image = pipe("A hyper-realistic portrait of a vpx man wearing iridescent neon armor, standing amidst the glowing flora of a bioluminescent alien jungle.", num_inference_steps=8, guidance_scale=0.0).images[0]
	image.save("output.png")
	```