引導式測驗 · 中等 等級
客製化擴散多概念調音測驗
查看自訂擴散的交叉注意調整、少量個性化、正則化以及組合多個概念的受支持方法。
問題 1 的 8
自訂擴散主要對擴散模型的哪一部分進行微調?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 自訂擴散主要對擴散模型的哪一部分進行微調?
- 交叉注意力層中的關鍵和價值投影
- U-Net 中的每個權重
- 僅 VAE 解碼器
- 文字分詞器
- 與單一概念方法相比,客製化擴散最值得注意的是什麼?
- 產生視訊而不是圖像
- 在一個場景中組合多個新學到的概念
- 根本不需要圖像
- 僅在 CPU 上運行
- What minimum number of training images did the Custom Diffusion paper report using in some experiments?
- As few as four images
- At least 500 images
- Exactly one image in every experiment
- The paper specifies no concept images
- 為什麼自訂擴散使用來自概念更廣泛類別的一組正規化影像?
- 加速 VAE
- 提高影像解析度
- 刪除浮水印
- 防止概念詞的過度擬合和語言漂移
- 兩個單獨訓練的自訂擴散概念如何一起使用?
- 透過對調整後的權重進行約束優化來合併它們
- 它們永遠不能結合在一起
- 透過對輸入影像進行平均
- 透過從頭開始重新訓練完整模型
- What proportion of model weights did the Custom Diffusion paper report storing for its tuned subset?
- About 3% of the model weights
- All model weights plus a new model copy
- No trained parameters at all
- A fixed 50% of the model weights
- Besides merging separately tuned models, how does Custom Diffusion support learning multiple concepts?
- It requires a separate foundation model for every prompt
- It replaces all cross-attention with a fixed lookup table
- It can train for multiple concepts jointly
- It can only learn one concept per model
- In a cross-attention layer, what do the tuned text-side key and value projections help associate?
- Image pixels with internet search results
- The diffusion timestep with the model's source code
- Audio frequencies with a document's page number
- Prompt concepts with features in the image latent representation