Diffusion models continuously push the boundary of state-of-the-art image generation, but the process is hard to control with any nuance: practice proves that textual prompts are inadequate for accurately describing image style or fine structural details (such as faces). ControlNet [43] and IPAdapter [39] address this shortcoming by conditioning the generative process on imagery instead, but each individual instance is limited to modeling a single conditional posterior: for practical use-cases, where multiple different posteriors are desired within the same workflow, training and using multiple adapters is cumbersome. We propose IPAdapter-Instruct, which combines natural-image conditioning with “Instruct” prompts to swap between interpretations for the same conditioning image: style transfer, object extraction, both, or something else still? IPAdapterInstruct efficiently learns multiple tasks with minimal loss in quality compared to dedicated per-task models.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

IPAdapter-Instruct: Resolving Ambiguity in Image-Based Conditioning Using Instruct Prompts

  • Ciara Rowles,
  • Shimon Vainer,
  • Dante De Nigris,
  • Slava Elizarov,
  • Konstantin Kutsy,
  • Simon Donné

摘要

Diffusion models continuously push the boundary of state-of-the-art image generation, but the process is hard to control with any nuance: practice proves that textual prompts are inadequate for accurately describing image style or fine structural details (such as faces). ControlNet [43] and IPAdapter [39] address this shortcoming by conditioning the generative process on imagery instead, but each individual instance is limited to modeling a single conditional posterior: for practical use-cases, where multiple different posteriors are desired within the same workflow, training and using multiple adapters is cumbersome. We propose IPAdapter-Instruct, which combines natural-image conditioning with “Instruct” prompts to swap between interpretations for the same conditioning image: style transfer, object extraction, both, or something else still? IPAdapterInstruct efficiently learns multiple tasks with minimal loss in quality compared to dedicated per-task models.