{"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/shifted-diffusion-for-text-to-image","title":"Shifted Diffusion for Text-to-image Generation","arxiv_id":"2211.15388","date":"2022-11-24","proceeding":"CVPR 2023 1","authors":["Yufan Zhou","Bingchen Liu","Yizhe Zhu","Xiao Yang","Changyou Chen","Jinhui Xu"],"abstract":"We present Corgi, a novel method for text-to-image generation. Corgi is based on our proposed shifted diffusion model, which achieves better image embedding generation from input text. Unlike the baseline diffusion model used in DALL-E 2, our method seamlessly encodes prior knowledge of the pre-trained CLIP model in its diffusion process by designing a new initialization distribution and a new transition step of the diffusion. Compared to the strong DALL-E 2 baseline, our method performs better in generating image embedding from the text in terms of both efficiency and effectiveness, resulting in better text-to-image generation. Extensive large-scale experiments are conducted and evaluated in terms of both quantitative measures and human evaluation, indicating a stronger generation ability of our method compared to existing ones. Furthermore, our model enables semi-supervised and language-free training for text-to-image generation, where only part or none of the images in the training dataset have an associated caption. Trained with only 1.7% of the images being captioned, our semi-supervised model obtains FID results comparable to DALL-E 2 on zero-shot text-to-image generation evaluated on MS-COCO. Corgi also achieves new state-of-the-art results across different datasets on downstream language-free text-to-image generation tasks, outperforming the previous method, Lafite, by a large margin.","url_abs":"https://arxiv.org/abs/2211.15388v2","url_pdf":"https://arxiv.org/pdf/2211.15388v2.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":"shifted-diffusion-for-text-to-image","repo_url":"https://github.com/drboog/Shifted_Diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"CC0-1.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"zero-shot-text-to-image-generation","task_name":"Zero-Shot Text-to-Image Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":null,"method_name":"None"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"Corgi-Semi","rank_in_archive_order":27,"of":69,"metrics":{"FID":"10.6"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"Corgi","rank_in_archive_order":28,"of":69,"metrics":{"FID":"10.88"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-multi-modal","task":"Text-to-Image Generation","dataset":"Multi-Modal-CelebA-HQ","model":"Corgi","rank_in_archive_order":3,"of":10,"metrics":{"FID":"19.74"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.15388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.15388"}},"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/drboog/Shifted_Diffusion","reach":{"status":"ok","spdx":"CC0-1.0"}}],"summary":{"ran_draft_wrong":3,"ran":1,"ran_honours":2,"ran_violates":1,"unverified":10},"by_repo_kind":{"official":{"samples":17,"ran":7,"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":"cfd76fd0d89574a4","entry":"approx_standard_normal_cdf","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/losses.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cfd76fd0d89574a4"}},{"code_sha256_prefix":"4e2ac192b520c457","entry":"args_to_dict","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/script_util.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/script_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e2ac192b520c457"}},{"code_sha256_prefix":"2ab2316ac6fdd869","entry":"betas_for_alpha_bar","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/gaussian_diffusion.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/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":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ab2316ac6fdd869"}},{"code_sha256_prefix":"cd33283d615fb3d7","entry":"discretized_gaussian_log_likelihood","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/losses.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd33283d615fb3d7"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/losses.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/losses.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cf2798b666b231ca"}},{"code_sha256_prefix":"721eef93e7a633a1","entry":"str2bool","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/script_util.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/script_util.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"721eef93e7a633a1"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/nn.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/nn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"129b804760b3115f"}},{"code_sha256_prefix":"0b6af1610028f48b","entry":"alpha_schedules","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b6af1610028f48b"}},{"code_sha256_prefix":"ecd0fc28815b65ae","entry":"avg_pool_nd","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/nn.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ecd0fc28815b65ae"}},{"code_sha256_prefix":"fe4eb545bbb728e0","entry":"conv_nd","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/nn.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe4eb545bbb728e0"}},{"code_sha256_prefix":"74468cb5afcdceba","entry":"create_named_schedule_sampler","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/resample.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/resample.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74468cb5afcdceba"}},{"code_sha256_prefix":"b1986232479684ae","entry":"file_ext","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"process_img.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/process_img.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b1986232479684ae"}},{"code_sha256_prefix":"6431708d8f3ff177","entry":"get_full_repo_name","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/finetune.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6431708d8f3ff177"}},{"code_sha256_prefix":"7b3d746840b3d405","entry":"get_named_beta_schedule","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/gaussian_diffusion.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7b3d746840b3d405"}},{"code_sha256_prefix":"c849cc3a392127d7","entry":"gumbel_noised","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c849cc3a392127d7"}},{"code_sha256_prefix":"815ff46e50dd7353","entry":"index_to_log_onehot","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/diffusers/src/diffusers/schedulers/scheduling_vq_diffusion.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"815ff46e50dd7353"}},{"code_sha256_prefix":"9afcec4ee15ce58d","entry":"space_timesteps","repo":"drboog/Shifted_Diffusion","repo_kind":"official","path":"model_lib/diffusion/respace.py","file_url":"https://github.com/drboog/Shifted_Diffusion/blob/HEAD/model_lib/diffusion/respace.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9afcec4ee15ce58d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}