{"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/terdit-ternary-diffusion-models-with","title":"TerDiT: Ternary Diffusion Models with Transformers","arxiv_id":"2405.14854","date":"2024-05-23","proceeding":null,"authors":["Xudong Lu","Aojun Zhou","Ziyi Lin","Qi Liu","Yuhui Xu","Renrui Zhang","Yafei Wen","Shuai Ren","Peng Gao","Junchi Yan","Hongsheng Li"],"abstract":"Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion models based on transformer architecture (DiTs). Among these diffusion models, diffusion transformers have demonstrated superior image generation capabilities, boosting lower FID scores and higher scalability. However, deploying large-scale DiT models can be expensive due to their extensive parameter numbers. Although existing research has explored efficient deployment techniques for diffusion models such as model quantization, there is still little work concerning DiT-based models. To tackle this research gap, in this paper, we propose TerDiT, a quantization-aware training (QAT) and efficient deployment scheme for ternary diffusion models with transformers. We focus on the ternarization of DiT networks and scale model sizes from 600M to 4.2B. Our work contributes to the exploration of efficient deployment strategies for large-scale DiT models, demonstrating the feasibility of training extremely low-bit diffusion transformer models from scratch while maintaining competitive image generation capacities compared to full-precision models. Code will be available at https://github.com/Lucky-Lance/TerDiT.","url_abs":"https://arxiv.org/abs/2405.14854v1","url_pdf":"https://arxiv.org/pdf/2405.14854v1.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":"terdit-ternary-diffusion-models-with","repo_url":"https://github.com/Lucky-Lance/TerDiT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.14854","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14854"}},"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/Lucky-Lance/TerDiT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran":1,"ran_honours":3,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":12,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"d6a68e210556f857","entry":"approx_standard_normal_cdf","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6a68e210556f857"}},{"code_sha256_prefix":"ab1c9568b4e13899","entry":"continuous_gaussian_log_likelihood","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab1c9568b4e13899"}},{"code_sha256_prefix":"84d035114dad12a2","entry":"export","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"models.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"84d035114dad12a2"}},{"code_sha256_prefix":"3e0fa4efc22272d4","entry":"get_beta_schedule","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e0fa4efc22272d4"}},{"code_sha256_prefix":"36e30c7fb679ec78","entry":"get_named_beta_schedule","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"36e30c7fb679ec78"}},{"code_sha256_prefix":"f6d7c009a8efb8b7","entry":"mean_flat","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6d7c009a8efb8b7"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"models.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03310bba324ae4fb"}},{"code_sha256_prefix":"8afbfc42c6ea0448","entry":"normal_kl","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8afbfc42c6ea0448"}},{"code_sha256_prefix":"ea9dbc131adf582e","entry":"space_timesteps","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/respace.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/respace.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea9dbc131adf582e"}},{"code_sha256_prefix":"e48218d7d73db0b3","entry":"create_named_schedule_sampler","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"diffusion/timestep_sampler.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/diffusion/timestep_sampler.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":"e48218d7d73db0b3"}},{"code_sha256_prefix":"a45844bbbc818cb3","entry":"get_device","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"fairscale/benchmarks/fsdp.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/fairscale/benchmarks/fsdp.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":"a45844bbbc818cb3"}},{"code_sha256_prefix":"d457115aa40f2a97","entry":"get_problem","repo":"Lucky-Lance/TerDiT","repo_kind":"official","path":"fairscale/benchmarks/oss.py","file_url":"https://github.com/Lucky-Lance/TerDiT/blob/HEAD/fairscale/benchmarks/oss.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":"d457115aa40f2a97"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}