import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("irodkin/controlnet_celeba_with_llava_captions_ft", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]For this model the only one available contol input is the conditioning_image from dataset irodkin/celeba_with_llava_shorter_captions
And this image the model actually ignores. Its just experimental text2image
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support