import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ashen0209/Flux-Consistancy-v2", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This adapter for Flux-dev is to generate consistancy character based on one or multiple reference images. It is an improved version that adds supports to multiple reference based on https://huggingface.co/ashen0209/Flux-Character-Consitancy. You can try it in this space https://huggingface.co/spaces/ashen0209/Flux-Consistancy-v2.
Here are the showcases for couple generation:
As GPT-4o's native image generation is set to unify all visual generation tasks, I'm releasing this model ahead of schedule—leaving past work behind and perhaps embarking on something new
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support