{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/fusedream-training-free-text-to-image","title":"FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization","arxiv_id":"2112.01573","date":"2021-12-02","proceeding":null,"authors":["Xingchao Liu","Chengyue Gong","Lemeng Wu","Shujian Zhang","Hao Su","Qiang Liu"],"abstract":"Generating images from natural language instructions is an intriguing yet highly challenging task. We approach text-to-image generation by combining the power of the retrained CLIP representation with an off-the-shelf image generator (GANs), optimizing in the latent space of GAN to find images that achieve maximum CLIP score with the given input text. Compared to traditional methods that train generative models from text to image starting from scratch, the CLIP+GAN approach is training-free, zero shot and can be easily customized with different generators. However, optimizing CLIP score in the GAN space casts a highly challenging optimization problem and off-the-shelf optimizers such as Adam fail to yield satisfying results. In this work, we propose a FuseDream pipeline, which improves the CLIP+GAN approach with three key techniques: 1) an AugCLIP score which robustifies the CLIP objective by introducing random augmentation on image. 2) a novel initialization and over-parameterization strategy for optimization which allows us to efficiently navigate the non-convex landscape in GAN space. 3) a composed generation technique which, by leveraging a novel bi-level optimization formulation, can compose multiple images to extend the GAN space and overcome the data-bias. When promoted by different input text, FuseDream can generate high-quality images with varying objects, backgrounds, artistic styles, even novel counterfactual concepts that do not appear in the training data of the GAN we use. Quantitatively, the images generated by FuseDream yield top-level Inception score and FID score on MS COCO dataset, without additional architecture design or training. Our code is publicly available at \\url{https://github.com/gnobitab/FuseDream}.","url_abs":"https://arxiv.org/abs/2112.01573v1","url_pdf":"https://arxiv.org/pdf/2112.01573v1.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":"fusedream-training-free-text-to-image","repo_url":"https://github.com/gnobitab/fusedream","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":"navigate","task_name":"Navigate"},{"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"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"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":"FuseDream (few-shot, k=5)","rank_in_archive_order":45,"of":69,"metrics":{"FID":"21.16","Inception score":"34.26"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"FuseDream (k=5, 256)","rank_in_archive_order":46,"of":69,"metrics":{"FID":"21.16","Inception score":"34.26"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"FuseDream (k=10, 256)","rank_in_archive_order":47,"of":69,"metrics":{"FID":"21.89","Inception score":"34.67"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2112.01573","atlas_url":"https://app.syntology.ai/?focus=2112.01573","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2112.01573"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2112.01573\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2112.01573"},"call":"get_concepts_for_paper(arxiv_id=\"2112.01573\")"}],"by_repo":[{"repo":"gnobitab/fusedream","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2304.13742"],"harvested_for_calls":[{"arxiv_id":"2304.13742","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2304.13742"},"call":"get_harvested_code_for_paper(arxiv_id=\"2304.13742\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"9a7a9307235e09626602f19d88118b2d6271b60891eaa27266aefcb5d9848f57","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}