{"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/vidit-q-efficient-and-accurate-quantization","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","arxiv_id":"2406.02540","date":"2024-06-04","proceeding":null,"authors":["Tianchen Zhao","Tongcheng Fang","Enshu Liu","Rui Wan","Widyadewi Soedarmadji","Shiyao Li","Zinan Lin","Guohao Dai","Shengen Yan","Huazhong Yang","Xuefei Ning","Yu Wang"],"abstract":"Diffusion transformers (DiTs) have exhibited remarkable performance in visual generation tasks, such as generating realistic images or videos based on textual instructions. However, larger model sizes and multi-frame processing for video generation lead to increased computational and memory costs, posing challenges for practical deployment on edge devices. Post-Training Quantization (PTQ) is an effective method for reducing memory costs and computational complexity. When quantizing diffusion transformers, we find that applying existing diffusion quantization methods designed for U-Net faces challenges in preserving quality. After analyzing the major challenges for quantizing diffusion transformers, we design an improved quantization scheme: \"ViDiT-Q\": Video and Image Diffusion Transformer Quantization) to address these issues. Furthermore, we identify highly sensitive layers and timesteps hinder quantization for lower bit-widths. To tackle this, we improve ViDiT-Q with a novel metric-decoupled mixed-precision quantization method (ViDiT-Q-MP). We validate the effectiveness of ViDiT-Q across a variety of text-to-image and video models. While baseline quantization methods fail at W8A8 and produce unreadable content at W4A8, ViDiT-Q achieves lossless W8A8 quantization. ViDiTQ-MP achieves W4A8 with negligible visual quality degradation, resulting in a 2.5x memory optimization and a 1.5x latency speedup.","url_abs":"https://arxiv.org/abs/2406.02540v2","url_pdf":"https://arxiv.org/pdf/2406.02540v2.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":"vidit-q-efficient-and-accurate-quantization","repo_url":"https://github.com/a-suozhang/vidit-q","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.02540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02540"}},"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/a-suozhang/vidit-q","reach":{"status":"ok"}}],"summary":{"ran":2,"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":10,"ran":3,"repositories":1}},"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":10,"samples":[{"code_sha256_prefix":"be410f653fadfc80","entry":"apply_func_to_submodules","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"quant_utils/qdiff/utils.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/quant_utils/qdiff/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be410f653fadfc80"}},{"code_sha256_prefix":"8dc23283b78375ff","entry":"extract_number_customize","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"eval/video/metrics/clip_score.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/eval/video/metrics/clip_score.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8dc23283b78375ff"}},{"code_sha256_prefix":"44b99c943200d432","entry":"open_image","repo":"A-suozhang/ViDiT-Q","repo_kind":"official","path":"eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.py","file_url":"https://github.com/A-suozhang/ViDiT-Q/blob/HEAD/eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.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":"44b99c943200d432"}},{"code_sha256_prefix":"a530bdcaf456e5c8","entry":"calc_probs_for_dataset","repo":"A-suozhang/ViDiT-Q","repo_kind":"official","path":"eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.py","file_url":"https://github.com/A-suozhang/ViDiT-Q/blob/HEAD/eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.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":"a530bdcaf456e5c8"}},{"code_sha256_prefix":"40c33c72d49ca85f","entry":"calculate_activation_statistics","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"eval/image/evaluation/fid_score.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/eval/image/evaluation/fid_score.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":"40c33c72d49ca85f"}},{"code_sha256_prefix":"2aed6e00d59aba70","entry":"calculate_clip_score","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"eval/video/metrics/clip_score.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/eval/video/metrics/clip_score.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":"2aed6e00d59aba70"}},{"code_sha256_prefix":"7bff88199cee559a","entry":"calculate_clip_temp_score","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"eval/video/metrics/clip_score.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/eval/video/metrics/clip_score.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":"7bff88199cee559a"}},{"code_sha256_prefix":"0def50a351111624","entry":"calculate_frechet_distance","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"eval/image/evaluation/fid_score.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/eval/image/evaluation/fid_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0def50a351111624"}},{"code_sha256_prefix":"7961d0b08426e139","entry":"get_activations","repo":"a-suozhang/vidit-q","repo_kind":"official","path":"eval/image/evaluation/fid_score.py","file_url":"https://github.com/a-suozhang/vidit-q/blob/HEAD/eval/image/evaluation/fid_score.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":"7961d0b08426e139"}},{"code_sha256_prefix":"ee8210e9a8649299","entry":"infer_example","repo":"A-suozhang/ViDiT-Q","repo_kind":"official","path":"eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.py","file_url":"https://github.com/A-suozhang/ViDiT-Q/blob/HEAD/eval/image/evaluation/metrics/PickScore/trainer/scripts/eval_preference_predictor.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":"ee8210e9a8649299"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}