Papers › FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization

FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization

2 Dec 2021arXiv:2112.01573archive 2025-07-28

Xingchao Liu, Chengyue Gong, Lemeng Wu, Shujian Zhang, Hao Su, Qiang Liu

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 https://github.com/gnobitab/FuseDream.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

gnobitab/fusedream officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation (arXiv:2304.13742; that paper's own run record: 17 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image GenerationNavigateText to Image GenerationText-to-Image GenerationZero-Shot Text-to-Image Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) FuseDream (few-shot, k=5) FID 21.16 #45 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) FuseDream (few-shot, k=5) Inception score 34.26 #45 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) FuseDream (k=5, 256) FID 21.16 #46 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) FuseDream (k=5, 256) Inception score 34.26 #46 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) FuseDream (k=10, 256) FID 21.89 #47 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) FuseDream (k=10, 256) Inception score 34.67 #47 of 69 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

CLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections