import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("DFloat11/FLUX.1-Kontext-dev-DF11", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("TsienDragon/DreamOmni2")
prompt = "control 1"
image = pipe(prompt).images[0]- control 1
- control 2
- generate
DreamOmni2
- Prompt
- control 1
- Prompt
- control 2
- Prompt
- generate
Model description
diffusers format of DreamOmni2 edit lroa
Download model
Download them in the Files & versions tab.
- Downloads last month
- -
Model tree for TsienDragon/DreamOmni2
Base model
black-forest-labs/FLUX.1-Kontext-dev Quantized
DFloat11/FLUX.1-Kontext-dev-DF11