| --- |
| library_name: diffusers |
| --- |
| |
| ## How to use |
|
|
| #### use ideogram-api to generate character using one input image |
|
|
| Get your Ideogram API token from [here](https://developer.ideogram.ai/ideogram-api/api-overview) |
|
|
| Set it as the `IDEOGRAM_API_KEY` environment variable: |
|
|
| ```py |
| 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=( |
| '''Youtube thumbnail of a women texting on iphone. Graphic overlay of text bubble "🤗"''' |
| ), |
| character_image=load_image(PATH_TO_IMAGE), |
| 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='''change the text to "when is next diffusers release?"''', |
| guidance_scale=1.5 |
| ).images[0] |
| ``` |
|
|
|
|
|
|
|  |
|
|
|
|
