{"id":20497153,"url":"https://github.com/fork123aniket/text-to-image-synthesis-using-stackgans","last_synced_at":"2026-04-20T14:36:08.276Z","repository":{"id":158619663,"uuid":"560354434","full_name":"fork123aniket/Text-to-Image-Synthesis-using-StackGANs","owner":"fork123aniket","description":"Implementation of StackGANs for text-to-image generation in Tensorflow","archived":false,"fork":false,"pushed_at":"2023-05-01T12:03:38.000Z","size":591,"stargazers_count":3,"open_issues_count":1,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-01-16T06:25:23.145Z","etag":null,"topics":["gans","generative-adversarial-network","generative-model","image-generation","keras-neural-networks","keras-tensorflow","stackgan","tensorflow","text-to-image-generation","text-to-image-synthesis"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/fork123aniket.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-11-01T10:03:03.000Z","updated_at":"2024-02-27T05:29:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"728afc9c-1529-484f-a6d5-c1bf31bc5ce1","html_url":"https://github.com/fork123aniket/Text-to-Image-Synthesis-using-StackGANs","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fork123aniket%2FText-to-Image-Synthesis-using-StackGANs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fork123aniket%2FText-to-Image-Synthesis-using-StackGANs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fork123aniket%2FText-to-Image-Synthesis-using-StackGANs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fork123aniket%2FText-to-Image-Synthesis-using-StackGANs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fork123aniket","download_url":"https://codeload.github.com/fork123aniket/Text-to-Image-Synthesis-using-StackGANs/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242087867,"owners_count":20069722,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["gans","generative-adversarial-network","generative-model","image-generation","keras-neural-networks","keras-tensorflow","stackgan","tensorflow","text-to-image-generation","text-to-image-synthesis"],"created_at":"2024-11-15T18:10:12.625Z","updated_at":"2026-04-20T14:36:03.234Z","avatar_url":"https://github.com/fork123aniket.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# StackGANs-based Text-to-Image Generation\n\nThis repository provides Stage-wise implementation of StackGANs to produce photo-realistic images from given text. The Stage-1 GAN sketches the primitive shape and colors of the object based on the given text description, yielding Stage-1 low-resolution images. On the other hand, The Stage-2 GAN takes Stage-1 results and text descriptions as inputs and generates high-resolution images with photo-realistic details. Moreover, it is able to rectify defects in Stage-1 results and add compelling details with the refinement process.\n\n## Requirements\n\n- `Python`\n- `tensorflow`\n- `keras`\n- `numpy`\n- `pandas`\n- `PIL`\n- `matplotlib`\n\n## Usage\n\n### Data\nThe training of StackGAN has been performed on CUB dataset. CUB contains 200 bird species with 11,788 images. Since 80% of birds in this dataset have object-image size ratios of less than 0.5, as a pre-processing step, cropping has been executed for all images to ensure that bounding boxes of birds have greater-than-0.75 object-image size ratios. The dataset can either be downloaded from [***here***](https://drive.google.com/open?id=0B3y_msrWZaXLT1BZdVdycDY5TEE) or can be obtained by running `wget http://www.vision.caltech.edu/visipedia-data/CUB-200-2011/CUB_200_2011.tgz` command.\n\n### Training and Testing\n- To train ***Stage-1 StackGAN*** : run `Train_Stage_1_GAN.py`\n- To test ***Stage-2 StackGAN*** : run `Train_Stage_2_GAN.py`\n- To see the ***Stage-1 StackGAN*** and ***Stage-2 StackGAN*** implementations, please check `Stage_1_GAN.py` and `Stage_2_GAN.py` respectively.\n- All hyperparameters to control training and testing of ***StackGANs*** are provided in `Train_Stage_1_GAN.py` and `Train_Stage_2_GAN.py` files.\n\n## Results\n\nThe eventual outcomes of both ***Stage-1 StackGAN*** and ***Stage-2 StackGAN*** can be seen against each given input text in the following attached image:-\n\n![alt text](https://github.com/fork123aniket/Text-to-Image-Synthesis-using-StackGANs/blob/main/Images/Result.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffork123aniket%2Ftext-to-image-synthesis-using-stackgans","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffork123aniket%2Ftext-to-image-synthesis-using-stackgans","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffork123aniket%2Ftext-to-image-synthesis-using-stackgans/lists"}