Instructions to use Fragile/lilyv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Fragile/lilyv2 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("Fragile/lilyv2") prompt = "A cinematic portrait of LilyV2 wearing ornate gold armor, standing amidst the glowing ruins of a futuristic cyberpunk city under a neon rain." image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Krea 2 LoRA β Fragile/lilyv2

- Prompt
- A cinematic portrait of LilyV2 wearing ornate gold armor, standing amidst the glowing ruins of a futuristic cyberpunk city under a neon rain.

- Prompt
- LilyV2 as a whimsical forest spirit, draped in translucent silk and wildflowers, floating softly above a bioluminescent pond in a mystical woodland.

- Prompt
- A high-fashion editorial shot of LilyV2 in a sharp velvet suit, posing inside a minimalist white marble gallery with dramatic architectural shadows.
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 LilyV2 to invoke the concept.
Samples
"A cinematic portrait of LilyV2 wearing ornate gold armor, standing amidst the glowing ruins of a futuristic cyberpunk city under a neon rain."
"LilyV2 as a whimsical forest spirit, draped in translucent silk and wildflowers, floating softly above a bioluminescent pond in a mystical woodland."
"A high-fashion editorial shot of LilyV2 in a sharp velvet suit, posing inside a minimalist white marble gallery with dramatic architectural shadows."
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("Fragile/lilyv2")
image = pipe("A cinematic portrait of LilyV2 wearing ornate gold armor, standing amidst the glowing ruins of a futuristic cyberpunk city under a neon rain.", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 15
Model tree for Fragile/lilyv2
Base model
krea/Krea-2-Raw

