{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/190600446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","arxiv_id":"1906.00446","date":"2019-06-02","proceeding":"NeurIPS 2019 12","authors":["Ali Razavi","Aaron van den Oord","Oriol Vinyals"],"abstract":"We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation. To this end, we scale and enhance the autoregressive priors used in VQ-VAE to generate synthetic samples of much higher coherence and fidelity than possible before. We use simple feed-forward encoder and decoder networks, making our model an attractive candidate for applications where the encoding and/or decoding speed is critical. Additionally, VQ-VAE requires sampling an autoregressive model only in the compressed latent space, which is an order of magnitude faster than sampling in the pixel space, especially for large images. We demonstrate that a multi-scale hierarchical organization of VQ-VAE, augmented with powerful priors over the latent codes, is able to generate samples with quality that rivals that of state of the art Generative Adversarial Networks on multifaceted datasets such as ImageNet, while not suffering from GAN's known shortcomings such as mode collapse and lack of diversity.","url_abs":"https://arxiv.org/abs/1906.00446v1","url_pdf":"https://arxiv.org/pdf/1906.00446v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"190600446","repo_url":"https://github.com/deepmind/sonnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"190600446","repo_url":"https://github.com/eric-yim/distribution_reconstruction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"190600446","repo_url":"https://github.com/eric-yim/image_reconstruction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"190600446","repo_url":"https://github.com/eric-yim/vqvae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"190600446","repo_url":"https://github.com/mattiasxu/VQVAE-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"190600446","repo_url":"https://github.com/mattiasxu/Video-VQVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600446","repo_url":"https://github.com/seymayucer/VAEs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600446","repo_url":"https://github.com/skymanaditya1/FaceOff","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"190600446","repo_url":"https://github.com/superizer/vqvae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"190600446","repo_url":"https://github.com/tgisaturday/dalle-lightning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"190600446","repo_url":"https://github.com/tgisaturday/dalle-lightning-tpu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"190600446","repo_url":"https://github.com/tgisaturday/taming-transformers-tpu","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"unanswered"}},{"paper_slug":"190600446","repo_url":"https://github.com/vvvm23/vqvae-2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"190600446","repo_url":"https://github.com/EugenHotaj/pytorch-generative/blob/master/pytorch_generative/models/vae/vq_vae_2.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"190600446","repo_url":"https://github.com/rosinality/vq-vae-2-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"high","task_name":"Vocal Bursts Intensity Prediction"}],"methods":[{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"pixelcnn","method_name":"PixelCNN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"vq-vae-2","method_name":"VQ-VAE-2"}],"datasets_introduced":[],"methods_introduced":[{"slug":"vq-vae-2","name":"VQ-VAE-2","full_name":"VQ-VAE-2"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.00446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00446"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mattiasxu/Video-VQVAE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vvvm23/vqvae-2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/EugenHotaj/pytorch-generative/blob/master/pytorch_generative/models/vae/vq_vae_2.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eric-yim/vqvae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/superizer/vqvae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eric-yim/image_reconstruction","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/sonnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tgisaturday/taming-transformers-tpu","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tgisaturday/dalle-lightning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mattiasxu/VQVAE-2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/seymayucer/VAEs","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/skymanaditya1/FaceOff","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tgisaturday/dalle-lightning-tpu","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rosinality/vq-vae-2-pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eric-yim/distribution_reconstruction","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"ran_violates":1,"unverified":7},"by_repo_kind":{"listed":{"samples":9,"ran":2,"repositories":5}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"814630e4695f80ad","entry":"load_checkpoint","repo":"seymayucer/VAEs","repo_kind":"listed","path":"train_vae.py","file_url":"https://github.com/seymayucer/VAEs/blob/HEAD/train_vae.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"814630e4695f80ad"}},{"code_sha256_prefix":"75227e193ad3d9a8","entry":"reverse_norm","repo":"eric-yim/image_reconstruction","repo_kind":"listed","path":"vq_train.py","file_url":"https://github.com/eric-yim/image_reconstruction/blob/HEAD/vq_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75227e193ad3d9a8"}},{"code_sha256_prefix":"991e7e9220881de1","entry":"causal_mask","repo":"mattiasxu/VQVAE-2","repo_kind":"listed","path":"pixelsnail.py","file_url":"https://github.com/mattiasxu/VQVAE-2/blob/HEAD/pixelsnail.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"991e7e9220881de1"}},{"code_sha256_prefix":"461521d71ee2d6f4","entry":"elu_conv_elu","repo":"mattiasxu/VQVAE-2","repo_kind":"listed","path":"pixelsnail.py","file_url":"https://github.com/mattiasxu/VQVAE-2/blob/HEAD/pixelsnail.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"461521d71ee2d6f4"}},{"code_sha256_prefix":"6209bc911accf845","entry":"get_images","repo":"eric-yim/image_reconstruction","repo_kind":"listed","path":"test_results.py","file_url":"https://github.com/eric-yim/image_reconstruction/blob/HEAD/test_results.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6209bc911accf845"}},{"code_sha256_prefix":"6cd8f26aabe808a6","entry":"list_to_batch","repo":"eric-yim/image_reconstruction","repo_kind":"listed","path":"vq_train.py","file_url":"https://github.com/eric-yim/image_reconstruction/blob/HEAD/vq_train.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6cd8f26aabe808a6"}},{"code_sha256_prefix":"8125e02b1a44b90f","entry":"positional_encoding","repo":"mattiasxu/VQVAE-2","repo_kind":"listed","path":"pixelsnail.py","file_url":"https://github.com/mattiasxu/VQVAE-2/blob/HEAD/pixelsnail.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8125e02b1a44b90f"}},{"code_sha256_prefix":"420c9bfc99dd6d0b","entry":"reproduce","repo":"EugenHotaj/pytorch-generative","repo_kind":"listed","path":"pytorch_generative/models/vae/vq_vae_2.py","file_url":"https://github.com/EugenHotaj/pytorch-generative/blob/HEAD/pytorch_generative/models/vae/vq_vae_2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"420c9bfc99dd6d0b"}},{"code_sha256_prefix":"b614d6b615098ae0","entry":"vqvae_decode","repo":"vvvm23/vqvae-2","repo_kind":"listed","path":"main-sample.py","file_url":"https://github.com/vvvm23/vqvae-2/blob/HEAD/main-sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b614d6b615098ae0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}