import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("AlekseyCalvin/unMedusa_statue2life_Kontext_v2")
prompt = "unmedusa statue, convert to photo of the person, retaining same identity and composition"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]unMedusa (Statue to Life) Var.2
Low Rank Adapter (LoRA) for Flux KONTEXT Dev
|||| By Silver Age Poets ||||
Low-Rank Adapter (LoRA) for FLUX Kontext editing/instruction model(s)...
- Prompt
- unmedusa statue, convert to photo of the person, retaining same identity and composition
- Prompt
- unmedusa statue, convert to photo of the person, retaining same identity and composition
Prompt instruction
You should use unmedusa statue, convert to photo of the person, retaining same identity and composition, etc, as part of the prompt instruction for your image-to-image editing.
- Downloads last month
- 20
Model tree for AlekseyCalvin/unMedusa_statue2life_Kontext_v2
Base model
black-forest-labs/FLUX.1-Kontext-dev