{"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/intermediate-representations-for-enhanced","title":"Generating Intermediate Representations for Compositional Text-To-Image Generation","arxiv_id":"2410.09792","date":"2024-10-13","proceeding":null,"authors":["Ran Galun","Sagie Benaim"],"abstract":"Text-to-image diffusion models have demonstrated an impressive ability to produce high-quality outputs. However, they often struggle to accurately follow fine-grained spatial information in an input text. To this end, we propose a compositional approach for text-to-image generation based on two stages. In the first stage, we design a diffusion-based generative model to produce one or more aligned intermediate representations (such as depth or segmentation maps) conditioned on text. In the second stage, we map these representations, together with the text, to the final output image using a separate diffusion-based generative model. Our findings indicate that such compositional approach can improve image generation, resulting in a notable improvement in FID score and a comparable CLIP score, when compared to the standard non-compositional baseline.","url_abs":"https://arxiv.org/abs/2410.09792v2","url_pdf":"https://arxiv.org/pdf/2410.09792v2.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":"intermediate-representations-for-enhanced","repo_url":"https://github.com/rang1991/public-intermediate-semantics-for-generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"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"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.09792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09792"}},"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/rang1991/public-intermediate-semantics-for-generation","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"88bc9ba7e67563ce","entry":"create_canvas","repo":"rang1991/public-intermediate-semantics-for-generation","repo_kind":"official","path":"ControlnetGithub/gradio_scribble2image_interactive.py","file_url":"https://github.com/rang1991/public-intermediate-semantics-for-generation/blob/HEAD/ControlnetGithub/gradio_scribble2image_interactive.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88bc9ba7e67563ce"}},{"code_sha256_prefix":"0dbf855dab1ab575","entry":"get_node_name","repo":"rang1991/public-intermediate-semantics-for-generation","repo_kind":"official","path":"ControlnetGithub/tool_add_control.py","file_url":"https://github.com/rang1991/public-intermediate-semantics-for-generation/blob/HEAD/ControlnetGithub/tool_add_control.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0dbf855dab1ab575"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}