Upload README.md with huggingface_hub

0560740 verified 3 months ago

2.04 kB

---
base_model: krea/Krea-2-Raw
tags:
- text-to-image
- diffusers
- lora
- krea2
- template:sd-lora
license: apache-2.0
instance_prompt: "TRAPPED_BJ"
widget:
- text: "A majestic snow leopard leaping across a jagged Himalayan cliffside during a fierce blizzard, crystalline ice particles frozen in mid-air. TRAPPED_BJ"
  output:
    url: sample_0.png
- text: "A sleek, neon-lit cyberpunk hovercar speeding down a rain-slicked Tokyo highway at midnight, reflecting vibrant magenta and teal lights. TRAPPED_BJ"
  output:
    url: sample_1.png
- text: "An elderly clockmaker meticulously assembling a golden pocket watch in a dusty, sun-drenched attic filled with floating motes of light. TRAPPED_BJ"
  output:
    url: sample_2.png
---
# Krea 2 LoRA — funseshon/trapped-bj

<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 phrase `TRAPPED_BJ` to invoke the concept.

## Samples

![sample](./sample_0.png)

> *"A majestic snow leopard leaping across a jagged Himalayan cliffside during a fierce blizzard, crystalline ice particles frozen in mid-air. TRAPPED_BJ"*

![sample](./sample_1.png)

> *"A sleek, neon-lit cyberpunk hovercar speeding down a rain-slicked Tokyo highway at midnight, reflecting vibrant magenta and teal lights. TRAPPED_BJ"*

![sample](./sample_2.png)

> *"An elderly clockmaker meticulously assembling a golden pocket watch in a dusty, sun-drenched attic filled with floating motes of light. TRAPPED_BJ"*

## 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("funseshon/trapped-bj")
image = pipe("A majestic snow leopard leaping across a jagged Himalayan cliffside during a fierce blizzard, crystalline ice particles frozen in mid-air. TRAPPED_BJ", 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: "TRAPPED_BJ"
	widget:
	- text: "A majestic snow leopard leaping across a jagged Himalayan cliffside during a fierce blizzard, crystalline ice particles frozen in mid-air. TRAPPED_BJ"
	output:
	url: sample_0.png
	- text: "A sleek, neon-lit cyberpunk hovercar speeding down a rain-slicked Tokyo highway at midnight, reflecting vibrant magenta and teal lights. TRAPPED_BJ"
	output:
	url: sample_1.png
	- text: "An elderly clockmaker meticulously assembling a golden pocket watch in a dusty, sun-drenched attic filled with floating motes of light. TRAPPED_BJ"
	output:
	url: sample_2.png
	---

	# Krea 2 LoRA — funseshon/trapped-bj

	<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 phrase `TRAPPED_BJ` to invoke the concept.

	## Samples

	![sample](./sample_0.png)

	> "A majestic snow leopard leaping across a jagged Himalayan cliffside during a fierce blizzard, crystalline ice particles frozen in mid-air. TRAPPED_BJ"

	![sample](./sample_1.png)

	> "A sleek, neon-lit cyberpunk hovercar speeding down a rain-slicked Tokyo highway at midnight, reflecting vibrant magenta and teal lights. TRAPPED_BJ"

	![sample](./sample_2.png)

	> "An elderly clockmaker meticulously assembling a golden pocket watch in a dusty, sun-drenched attic filled with floating motes of light. TRAPPED_BJ"

	## 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("funseshon/trapped-bj")
	image = pipe("A majestic snow leopard leaping across a jagged Himalayan cliffside during a fierce blizzard, crystalline ice particles frozen in mid-air. TRAPPED_BJ", num_inference_steps=8, guidance_scale=0.0).images[0]
	image.save("output.png")
	```