{"full_name":"lucidrains/DALLE-pytorch","owner":"lucidrains","name":"DALLE-pytorch","shard":"1","url":"https://github.com/lucidrains/DALLE-pytorch","description":"Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch","homepage":"","topics":["artificial-intelligence","deep-learning","attention-mechanism","text-to-image","transformers","multi-modal"],"tag_pages":["artificial-intelligence","attention-mechanism","deep-learning","multi-modal","text-to-image","transformers"],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/108653?u=6d8a8e8d28f8512933d729d7503ae3e622d59c64&v=4","created_at":"2021-01-05T20:35:16Z","pushed_at":"2024-02-17T21:42:10Z","metrics":{"stars":5628,"forks":637,"watchers":91,"issues":277,"prs":128,"releases":180,"issues_open":120,"issues_closed":157,"prs_open":5,"prs_closed":28,"prs_merged":95,"discussions":36},"growth":{"day":{"stars":0,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[5629,5629,5628,5628,5628,5628,5628],"forks":[637,637,637,637,637,637,637],"watchers":[null,91,91,91,91,91,91],"issues_open":[null,120,120,120,120,120,120],"prs_open":[null,5,5,5,5,5,5]},"boards":{},"same_owner":[{"full_name":"lucidrains/x-transformers","name":"x-transformers","shard":"1","boards":{}}],"issues":[{"number":10,"title":"Results","comments":57,"created_at":"2021-01-07T15:05:01Z"},{"number":137,"title":"Reproducing DALL-E using DeepSpeed","comments":32,"created_at":"2021-03-29T17:05:31Z"},{"number":74,"title":"OpenAIVae implementation","comments":27,"created_at":"2021-03-09T17:37:31Z"},{"number":61,"title":"Typical training results","comments":17,"created_at":"2021-03-01T22:08:29Z"},{"number":301,"title":"CI / Tests for DALLE-pytorch","comments":16,"created_at":"2021-06-13T09:31:34Z"},{"number":192,"title":"Allowing for custom trained VQGAN during DALLE training","comments":14,"created_at":"2021-04-13T04:53:18Z"},{"number":170,"title":"\"adamw\" optimizer + weight decay = poor generations","comments":12,"created_at":"2021-04-06T20:49:44Z"},{"number":99,"title":"Kl Loss correction","comments":12,"created_at":"2021-03-17T07:21:58Z"}],"discussions":[{"number":460,"title":"Image Reconstruction Using DALLE-Pytorch for Higher Resolutions","comments":0,"category":"Show and tell","created_at":"2024-12-10T20:25:14Z"},{"number":437,"title":"Dall-E training with low ressources (cuda memory error)","comments":0,"category":"General","created_at":"2022-07-06T04:32:43Z"},{"number":429,"title":"Applying DALLE to Protein Imaging","comments":0,"category":"Show and tell","created_at":"2022-05-27T17:18:21Z"},{"number":423,"title":"I am trainning the network on 8 million Logos","comments":0,"category":"Q&A","created_at":"2022-04-02T21:48:31Z"},{"number":415,"title":"is it better to have many captions or fewer detailed captions?","comments":0,"category":"Q&A","created_at":"2022-02-10T09:54:37Z"},{"number":404,"title":".","comments":0,"category":"Q&A","created_at":"2021-12-31T23:28:57Z"},{"number":396,"title":"new 32 layer model","comments":2,"category":"Show and tell","created_at":"2021-12-01T17:43:57Z"},{"number":392,"title":"How do I rank  DALLE-pytorch output by using CLIP?","comments":0,"category":"Q&A","created_at":"2021-11-30T05:31:52Z"}],"latest_release":{"name":"1.6.6","tag":"1.6.6","published_at":"2023-05-24T18:40:03Z","body":"","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}