Working with BFL FLUX in Pixeltable

What it covers

• Text-to-Image Generation
• Image Editing
• Using Seeds for Reproducibility
• Image Expansion (Outpainting)
• Inpainting with Fill
• Best Practices
• Learn More

What it uses

Install

terminal

$pip install pixeltable

Environment variables it names

BFL_API_KEY

Pixeltable calls

bfl.generate()bfl.edit()bfl.expand()bfl.fill()pxt.create_table()add_computed_column()insert()

A look at the code

# Create a table for image generation
prompts_t = pxt.create_table(
    'bfl_demo.prompts',
    {'prompt': pxt.String, 'style': pxt.String},
    if_exists='replace',
)

# Add a computed column that generates images from prompts
prompts_t.add_computed_column(
    image=bfl.generate(
        prompts_t.prompt, model='flux-pro-1.1', width=1024, height=1024
    )
)

One cell of the notebook, copied as it is. Open it in Colab for the rest.

• Working with Deepseek in Pixeltable

  Pixeltable's Deepseek integration enables you to access Deepseek's LLM via the Deepseek API.

  Updated Oct 29, 2026Open in Colab

• Working with fal.ai in Pixeltable

  Pixeltable's fal.ai integration enables you to access fal.ai's fast inference models via the fal.ai API.

  Updated Aug 3, 2026Open in Colab

• Working with Microsoft Fabric

  Pixeltable's Microsoft Fabric integration enables you to access Azure OpenAI models within Microsoft Fabric notebook environments with automatic authentication.

  Updated Aug 3, 2026

• Working with Fireworks AI in Pixeltable

  Pixeltable's Fireworks integration enables you to access LLMs hosted on the Fireworks platform.

  Updated Oct 8, 2026Open in Colab