Picasoe
Collection
2 items • Updated • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("robiai/picasoe")
prompt = "an old tv, vhs, with \"Picasoe\" written on screen"
image = pipe(prompt).images[0]Picasoe
- Prompt
- an old tv, vhs, with "Picasoe" written on screen
Model description
Picasoe is a text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
Model Description
- Developed by: Robi Team
- Model type: text-to-image generative model
- Model Description: This model generates images based on text prompts.
- Blog Post: Read here
How to use?
The model is available via HuggingFace Inference API
from huggingface_hub import InferenceClient
client = InferenceClient(
provider="hf-inference",
api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx"
)
image = client.text_to_image(
"Astronaut riding a horse",
model="robiai/picasoe"
)
- Downloads last month
- 6
Model tree for robiai/picasoe
Base model
black-forest-labs/FLUX.1-dev