Instructions to use mobbrain/stitch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mobbrain/stitch 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("mobbrain/stitch") prompt = "A cinematic shot of Stitch wearing a tiny astronaut suit, floating weightlessly inside a futuristic neon-lit space station." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA β mobbrain/stitch

- Prompt
- A cinematic shot of Stitch wearing a tiny astronaut suit, floating weightlessly inside a futuristic neon-lit space station.

- Prompt
- A lush, macro photography shot of Stitch napping inside a giant tropical hibiscus flower during a soft summer rain.

- Prompt
- A moody, noir-style portrait of Stitch wearing a detective's trench coat and fedora, standing under a streetlamp in a rainy 1940s city.
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 Stitch to invoke the concept.
Samples
"A cinematic shot of Stitch wearing a tiny astronaut suit, floating weightlessly inside a futuristic neon-lit space station."
"A lush, macro photography shot of Stitch napping inside a giant tropical hibiscus flower during a soft summer rain."
"A moody, noir-style portrait of Stitch wearing a detective's trench coat and fedora, standing under a streetlamp in a rainy 1940s city."
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("mobbrain/stitch")
image = pipe("A cinematic shot of Stitch wearing a tiny astronaut suit, floating weightlessly inside a futuristic neon-lit space station.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- -
Model tree for mobbrain/stitch
Base model
krea/Krea-2-Raw

