{"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/2408-01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","arxiv_id":"2408.01181","date":"2024-08-02","proceeding":null,"authors":["Qian Zhang","Xiangzi Dai","Ninghua Yang","Xiang An","Ziyong Feng","Xingyu Ren"],"abstract":"VAR is a new generation paradigm that employs 'next-scale prediction' as opposed to 'next-token prediction'. This innovative transformation enables auto-regressive (AR) transformers to rapidly learn visual distributions and achieve robust generalization. However, the original VAR model is constrained to class-conditioned synthesis, relying solely on textual captions for guidance. In this paper, we introduce VAR-CLIP, a novel text-to-image model that integrates Visual Auto-Regressive techniques with the capabilities of CLIP. The VAR-CLIP framework encodes captions into text embeddings, which are then utilized as textual conditions for image generation. To facilitate training on extensive datasets, such as ImageNet, we have constructed a substantial image-text dataset leveraging BLIP2. Furthermore, we delve into the significance of word positioning within CLIP for the purpose of caption guidance. Extensive experiments confirm VAR-CLIP's proficiency in generating fantasy images with high fidelity, textual congruence, and aesthetic excellence. Our project page are https://github.com/daixiangzi/VAR-CLIP","url_abs":"https://arxiv.org/abs/2408.01181v1","url_pdf":"https://arxiv.org/pdf/2408.01181v1.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":"2408-01181","repo_url":"https://github.com/daixiangzi/var-clip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.01181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.01181"}},"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/daixiangzi/var-clip","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":4,"ran":3,"ran_fixture":1,"unverified":5},"by_repo_kind":{"official":{"samples":13,"ran":8,"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":13,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/basic_vae.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/basic_vae.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"5be5e376692dd4c8","entry":"basic_clean","repo":"daixiangzi/var-clip","repo_kind":"official","path":"tokenizer/tokenizer.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/tokenizer/tokenizer.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":"5be5e376692dd4c8"}},{"code_sha256_prefix":"971ae8d2d8313e30","entry":"drop_path","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/helpers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"daixiangzi/var-clip","repo_kind":"official","path":"tokenizer/tokenizer.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/tokenizer/tokenizer.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"e543491ea064c733","entry":"gumbel_softmax_with_rng","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/helpers.py","link_basis":"harvester_set","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":"e543491ea064c733"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/basic_vae.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/basic_vae.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"80371584448f2f6e","entry":"sample_with_top_k_top_p_","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/helpers.py","link_basis":"harvester_set","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":"80371584448f2f6e"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"daixiangzi/var-clip","repo_kind":"official","path":"tokenizer/tokenizer.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/tokenizer/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"e847ee15f089dee6","entry":"allgather","repo":"daixiangzi/var-clip","repo_kind":"official","path":"dist.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/dist.py","link_basis":"harvester_set","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":"e847ee15f089dee6"}},{"code_sha256_prefix":"ff4c548fd07140d0","entry":"allreduce","repo":"daixiangzi/var-clip","repo_kind":"official","path":"dist.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/dist.py","link_basis":"harvester_set","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":"ff4c548fd07140d0"}},{"code_sha256_prefix":"1e42f58233e8bc6d","entry":"clip_vit_b32","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/clip.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/clip.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":"1e42f58233e8bc6d"}},{"code_sha256_prefix":"793c7e2489dd8dfc","entry":"make_attn","repo":"daixiangzi/var-clip","repo_kind":"official","path":"models/basic_vae.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/models/basic_vae.py","link_basis":"harvester_set","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":"793c7e2489dd8dfc"}},{"code_sha256_prefix":"826ea3fc406a6a09","entry":"new_group","repo":"daixiangzi/var-clip","repo_kind":"official","path":"dist.py","file_url":"https://github.com/daixiangzi/var-clip/blob/HEAD/dist.py","link_basis":"harvester_set","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":"826ea3fc406a6a09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}