Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929458735218688 |
|---|---|
| author | Yang, Zhengyuan Wang, Jianfeng Li, Linjie Lin, Kevin Lin, Chung-Ching Liu, Zicheng Wang, Lijuan |
| author_facet | Yang, Zhengyuan Wang, Jianfeng Li, Linjie Lin, Kevin Lin, Chung-Ching Liu, Zicheng Wang, Lijuan |
| contents | We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models via iterative explorations. This enables them to efficiently convert their high-level generation ideas into effective T2I prompts that can produce good images. We investigate if systems based on large multimodal models (LMMs) can develop analogous multimodal self-refinement abilities that enable exploring unknown models or environments via self-refining tries. Idea2Img cyclically generates revised T2I prompts to synthesize draft images, and provides directional feedback for prompt revision, both conditioned on its memory of the probed T2I model's characteristics. The iterative self-refinement brings Idea2Img various advantages over vanilla T2I models. Notably, Idea2Img can process input ideas with interleaved image-text sequences, follow ideas with design instructions, and generate images of better semantic and visual qualities. The user preference study validates the efficacy of multimodal iterative self-refinement on automatic image design and generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08541 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation Yang, Zhengyuan Wang, Jianfeng Li, Linjie Lin, Kevin Lin, Chung-Ching Liu, Zicheng Wang, Lijuan Computer Vision and Pattern Recognition We introduce ``Idea to Image,'' a system that enables multimodal iterative self-refinement with GPT-4V(ision) for automatic image design and generation. Humans can quickly identify the characteristics of different text-to-image (T2I) models via iterative explorations. This enables them to efficiently convert their high-level generation ideas into effective T2I prompts that can produce good images. We investigate if systems based on large multimodal models (LMMs) can develop analogous multimodal self-refinement abilities that enable exploring unknown models or environments via self-refining tries. Idea2Img cyclically generates revised T2I prompts to synthesize draft images, and provides directional feedback for prompt revision, both conditioned on its memory of the probed T2I model's characteristics. The iterative self-refinement brings Idea2Img various advantages over vanilla T2I models. Notably, Idea2Img can process input ideas with interleaved image-text sequences, follow ideas with design instructions, and generate images of better semantic and visual qualities. The user preference study validates the efficacy of multimodal iterative self-refinement on automatic image design and generation. |
| title | Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.08541 |