Instructions to use schrottteil/ashkrea with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use schrottteil/ashkrea 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-Raw", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("schrottteil/ashkrea") prompt = "A futuristic cyberpunk city street at midnight with neon signs reflecting in rain puddles, featuring a holographic MAsh display floating above the crowd." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA β schrottteil/ashkrea

- Prompt
- A futuristic cyberpunk city street at midnight with neon signs reflecting in rain puddles, featuring a holographic MAsh display floating above the crowd.

- Prompt
- A serene, sun-drenched Tuscan vineyard during golden hour, where a rustic wooden table holds a handcrafted MAsh ceramic sculpture.

- Prompt
- An epic cinematic shot of an ancient underwater civilization with bioluminescent coral reefs and a giant stone MAsh monument guarding the temple gates.
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 MAsh to invoke the concept.
Samples
"A futuristic cyberpunk city street at midnight with neon signs reflecting in rain puddles, featuring a holographic MAsh display floating above the crowd."
"A serene, sun-drenched Tuscan vineyard during golden hour, where a rustic wooden table holds a handcrafted MAsh ceramic sculpture."
"An epic cinematic shot of an ancient underwater civilization with bioluminescent coral reefs and a giant stone MAsh monument guarding the temple gates."
Use it with diffusers
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("schrottteil/ashkrea")
image = pipe("A futuristic cyberpunk city street at midnight with neon signs reflecting in rain puddles, featuring a holographic MAsh display floating above the crowd.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 25
Model tree for schrottteil/ashkrea
Base model
krea/Krea-2-Raw

