mill2 / README.md
gabai's picture
Upload README.md with huggingface_hub
e1faf89 verified
|
Raw
History Blame Contribute Delete
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: "M1ll3"
widget:
- text: "A cinematic shot of a futuristic cyberpunk city street drenched in neon rain, featuring a glowing holographic M1ll3 sign floating above a crowded marketplace."
output:
url: sample_0.png
- text: "An ethereal oil painting of a serene alpine meadow at sunrise, where a rustic wooden M1ll3 sits quietly beside a crystal-clear glacial stream."
output:
url: sample_1.png
- text: "A macro photography shot of a high-tech laboratory petri dish, showing a microscopic metallic M1ll3 structure assembling itself through nanotechnology."
output:
url: sample_2.png
---
# Krea 2 LoRA — gabai/mill2
<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 `M1ll3` to invoke the concept.
## Samples
![sample](./sample_0.png)
> *"A cinematic shot of a futuristic cyberpunk city street drenched in neon rain, featuring a glowing holographic M1ll3 sign floating above a crowded marketplace."*
![sample](./sample_1.png)
> *"An ethereal oil painting of a serene alpine meadow at sunrise, where a rustic wooden M1ll3 sits quietly beside a crystal-clear glacial stream."*
![sample](./sample_2.png)
> *"A macro photography shot of a high-tech laboratory petri dish, showing a microscopic metallic M1ll3 structure assembling itself through nanotechnology."*
## 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("gabai/mill2")
image = pipe("A cinematic shot of a futuristic cyberpunk city street drenched in neon rain, featuring a glowing holographic M1ll3 sign floating above a crowded marketplace.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
```