Diffusion Self-Distillation for Zero-Shot Customized Image Generation

• URL: http://arxiv.org/abs/2411.18616v1
• Date: Wed, 27 Nov 2024 18:58:52 GMT
• Title: Diffusion Self-Distillation for Zero-Shot Customized Image Generation
• Authors: Shengqu Cai, Eric Chan, Yunzhi Zhang, Leonidas Guibas, Jiajun Wu, Gordon Wetzstein,
• Abstract summary: Diffusion Self-Distillation is a method for generating its own dataset for text-conditioned image-to-image tasks. We first leverage a text-to-image diffusion model's in-context generation ability to create grids of images. We then fine-tune the text-to-image model into a text+image-to-image model using the curated paired dataset.
• Score: 40.11194010431839
• License:
• Abstract: Text-to-image diffusion models produce impressive results but are frustrating tools for artists who desire fine-grained control. For example, a common use case is to create images of a specific instance in novel contexts, i.e., "identity-preserving generation". This setting, along with many other tasks (e.g., relighting), is a natural fit for image+text-conditional generative models. However, there is insufficient high-quality paired data to train such a model directly. We propose Diffusion Self-Distillation, a method for using a pre-trained text-to-image model to generate its own dataset for text-conditioned image-to-image tasks. We first leverage a text-to-image diffusion model's in-context generation ability to create grids of images and curate a large paired dataset with the help of a Visual-Language Model. We then fine-tune the text-to-image model into a text+image-to-image model using the curated paired dataset. We demonstrate that Diffusion Self-Distillation outperforms existing zero-shot methods and is competitive with per-instance tuning techniques on a wide range of identity-preservation generation tasks, without requiring test-time optimization.

Related papers

• CLIP-VQDiffusion : Langauge Free Training of Text To Image generation using CLIP and vector quantized diffusion model [2.9849290402462927]
  We propose CLIP-VQDiffusion, which leverage the pretrained CLIP model to provide multimodal text-image representations and strong image generation capabilities. Our model outperformed previous state-of-the-art methods by 4.4% in clipscore and generated very realistic images even when the text was both in and out of distribution.
  arXiv  Detail & Related papers  (2024-03-22T04:34:59Z)
• Scene Graph Conditioning in Latent Diffusion [0.0]
  Diffusion models excel in image generation but lack detailed semantic control using text prompts. In contrast, scene graphs offer a more precise representation of image content. We show that using out proposed methods it is possible to generate images from scene graphs with much higher quality.
  arXiv  Detail & Related papers  (2023-10-16T12:26:01Z)
• Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency [47.3163261953469]
  Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. We introduce ITIT: an innovative training paradigm grounded in the concept of cycle consistency which allows vision-language training on unpaired image and text data. ITIT is comprised of a joint image-text encoder with disjoint image and text decoders that enable bidirectional image-to-text and text-to-image generation in a single framework.
  arXiv  Detail & Related papers  (2023-10-05T17:55:19Z)
• Generating Images with Multimodal Language Models [78.6660334861137]
  We propose a method to fuse frozen text-only large language models with pre-trained image encoder and decoder models. Our model demonstrates a wide suite of multimodal capabilities: image retrieval, novel image generation, and multimodal dialogue.
  arXiv  Detail & Related papers  (2023-05-26T19:22:03Z)
• GlyphDiffusion: Text Generation as Image Generation [100.98428068214736]
  We propose GlyphDiffusion, a novel diffusion approach for text generation via text-guided image generation. Our key idea is to render the target text as a glyph image containing visual language content. Our model also makes significant improvements compared to the recent diffusion model.
  arXiv  Detail & Related papers  (2023-04-25T02:14:44Z)
• Discriminative Class Tokens for Text-to-Image Diffusion Models [102.88033622546251]
  We propose a non-invasive fine-tuning technique that capitalizes on the expressive potential of free-form text. Our method is fast compared to prior fine-tuning methods and does not require a collection of in-class images. We evaluate our method extensively, showing that the generated images are: (i) more accurate and of higher quality than standard diffusion models, (ii) can be used to augment training data in a low-resource setting, and (iii) reveal information about the data used to train the guiding classifier.
  arXiv  Detail & Related papers  (2023-03-30T05:25:20Z)
• eDiffi: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers [87.52504764677226]
  Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. We train an ensemble of text-to-image diffusion models specialized for different stages synthesis. Our ensemble of diffusion models, called eDiffi, results in improved text alignment while maintaining the same inference cost.
  arXiv  Detail & Related papers  (2022-11-02T17:43:04Z)
• LAFITE: Towards Language-Free Training for Text-to-Image Generation [83.2935513540494]
  We propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model. We obtain state-of-the-art results in the standard text-to-image generation tasks.
  arXiv  Detail & Related papers  (2021-11-27T01:54:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.