Generate an image from text.
Explain a noise-to-image process.
Choose two correct statements.
Diffusion models learn adding and removing noise and can condition generation on text or image features; realism and factuality must be evaluated separately.
Detailed explanation
It can generate from a random state step by step.
It can generate from a random state step by step.
The result can be conditioned on input.
The result can be conditioned on input.
Realism and factuality are different.
Realism and factuality are different.
Randomness and settings can change output.
Randomness and settings can change output.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 2.1の生成モデル、拡散モデル、マルチモーダルを確認する。Expected result
拡散モデルの生成過程と、生成結果の限界を説明できる。Key points
- Noise
- Denoising
- Conditioning
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.