Yahoo Poland Wyszukiwanie w Internecie

Search results

1. arxiv.org › abs › 2301Muse: Text-To-Image Generation via Masked Generative Transformers

   arxiv.org › abs › 2301

   • Zapisane w pamięci cache

   2 sty 2023 · We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models.

2. openreview.net › forumMuse: Text-To-Image Generation via Masked Generative Transformers

   openreview.net › forum

   • Zapisane w pamięci cache

   24 kwi 2023 · Abstract: We present Muse, a text-to-image Transformermodel that achieves state-of-the-art image genera-tion performance while being significantly moreefficient than diffusion or autoregressive models.Muse is trained on a masked modeling task indiscrete token space: given the text embeddingextracted from a pre-trained large language model(LLM ...

3. paperswithcode.com › paper › muse-text-to-image-generation-via-maskedMuse: Text-To-Image Generation via Masked Generative Transformers

   paperswithcode.com › paper › muse-text-to-image-generation-via-masked

   • Zapisane w pamięci cache

   2 sty 2023 · We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models.

4. proceedings.mlr.press › v202 › chang23bMuse: Text-To-Image Generation via Masked Generative Transformers

   proceedings.mlr.press › v202 › chang23b

   We present Muse, a text-to-image Transformer model that achieves state-of-the-art image genera-tion performance while being significantly more efficient than diffusion or autoregressive models.

5. proceedings.mlr.press › v202 › chang23bMuse: Text-To-Image Generation via Masked Generative Transformers...

   proceedings.mlr.press › v202 › chang23b

   • Zapisane w pamięci cache

   Muse also directly enables anumber of image editing applications without theneed to fine-tune or invert the model: inpainting,outpainting, and mask-free editing. More resultsand videos demonstrating editing are available at https://muse-icml.github.io/

6. muse-model.github.ioMuse: Text-To-Image Generation via Masked Generative Transformers

   muse-model.github.io

   • Zapisane w pamięci cache

   Muse is a fast, state-of-the-art text-to-image generation and editing model. We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models.

7. github.com › huggingface › open-museGitHub - huggingface/open-muse: Open reproduction of MUSE for...

   github.com › huggingface › open-muse

   • Zapisane w pamięci cache

   An open-reproduction effort to reproduce the transformer based MUSE model for fast text2image generation.