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("AllwaysFurious/classicdnd")
prompt = "A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style"
image = pipe(prompt).images[0]Krea 2 LoRA — AllwaysFurious/classicdnd
- Prompt
- A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style
- Prompt
- A hooded plague doctor walking through a fog-drenched cobblestone alleyway lit by a single flickering lantern, dark fantasy ink style
- Prompt
- An ornate, decaying throne room overgrown with black thorny vines and shimmering ghostly embers, dark fantasy ink style
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 dark fantasy ink style to invoke the concept.
Samples
"A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style"
"A hooded plague doctor walking through a fog-drenched cobblestone alleyway lit by a single flickering lantern, dark fantasy ink style"
"An ornate, decaying throne room overgrown with black thorny vines and shimmering ghostly embers, dark fantasy ink style"
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("AllwaysFurious/classicdnd")
image = pipe("A colossal skeletal dragon coiled around a crumbling gothic spire under a blood-red moon, dark fantasy ink style", num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("output.png")
- Downloads last month
- 7
Model tree for AllwaysFurious/classicdnd
Base model
krea/Krea-2-Raw