{"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/cogview3-finer-and-faster-text-to-image","title":"CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion","arxiv_id":"2403.05121","date":"2024-03-08","proceeding":null,"authors":["Wendi Zheng","Jiayan Teng","Zhuoyi Yang","Weihan Wang","Jidong Chen","Xiaotao Gu","Yuxiao Dong","Ming Ding","Jie Tang"],"abstract":"Recent advancements in text-to-image generative systems have been largely driven by diffusion models. However, single-stage text-to-image diffusion models still face challenges, in terms of computational efficiency and the refinement of image details. To tackle the issue, we propose CogView3, an innovative cascaded framework that enhances the performance of text-to-image diffusion. CogView3 is the first model implementing relay diffusion in the realm of text-to-image generation, executing the task by first creating low-resolution images and subsequently applying relay-based super-resolution. This methodology not only results in competitive text-to-image outputs but also greatly reduces both training and inference costs. Our experimental results demonstrate that CogView3 outperforms SDXL, the current state-of-the-art open-source text-to-image diffusion model, by 77.0\\% in human evaluations, all while requiring only about 1/2 of the inference time. The distilled variant of CogView3 achieves comparable performance while only utilizing 1/10 of the inference time by SDXL.","url_abs":"https://arxiv.org/abs/2403.05121v1","url_pdf":"https://arxiv.org/pdf/2403.05121v1.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":"cogview3-finer-and-faster-text-to-image","repo_url":"https://github.com/thudm/cogview4","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"},{"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"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.05121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05121"}},"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/thudm/cogview4","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"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":"15543c2e826f861a","entry":"clean_string","repo":"thudm/cogview4","repo_kind":"listed","path":"inference/gradio_web_demo.py","file_url":"https://github.com/thudm/cogview4/blob/HEAD/inference/gradio_web_demo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15543c2e826f861a"}},{"code_sha256_prefix":"1dc10e5dc9582117","entry":"convert_prompt","repo":"thudm/cogview4","repo_kind":"listed","path":"inference/gradio_web_demo.py","file_url":"https://github.com/thudm/cogview4/blob/HEAD/inference/gradio_web_demo.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1dc10e5dc9582117"}},{"code_sha256_prefix":"6f07ed52231fad08","entry":"convert_prompt","repo":"thudm/cogview4","repo_kind":"listed","path":"inference/prompt_optimize.py","file_url":"https://github.com/thudm/cogview4/blob/HEAD/inference/prompt_optimize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f07ed52231fad08"}},{"code_sha256_prefix":"2bb0023884747d97","entry":"get_system_instruction","repo":"thudm/cogview4","repo_kind":"listed","path":"inference/prompt_optimize.py","file_url":"https://github.com/thudm/cogview4/blob/HEAD/inference/prompt_optimize.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2bb0023884747d97"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}