metadata
library_name: diffusers
use ideogram-api to generate character using one input image
Get your Ideogram API token from here
Set it as the IDEOGRAM_API_KEY environment variable:
from diffusers import ModularPipeline
from diffusers.utils import load_image
character_pipe = ModularPipeline.from_pretrained("diffusers-internal-dev/ideogram-character-generator", trust_remote_code=True)
print(character_pipe.doc)
image = character_pipe(
prompt=(
"medium shot (waist-up) of an Asian woman, full upper body clearly visible, "
"wearing a T-shirt with the text 'Modular Diffusers' legible on the chest, natural lighting, "
"professional photography style"
),
character_image=load_image("yiyi_3.jpg"),
output="image"
)
image.save("yiyi_character.png")
use with Flux Kontext
from diffusers import FluxKontextPipeline
import torch
pipe = FluxKontextPipeline.from_pretrained("black-forest-labs/FLUX.1-Kontext-dev", torch_dtype=torch.bfloat16)
pipe.to("cuda")
image = pipe(
image=image,
prompt='''standing in front of a coffee shop entrace with text "Huggingface". Do not change the character.''',
guidance_scale=1.5
).images[0]
