{"id":24206470,"url":"https://github.com/olaviinha/neuraltexttoimage","last_synced_at":"2025-10-28T18:19:11.393Z","repository":{"id":57814418,"uuid":"387449477","full_name":"olaviinha/NeuralTextToImage","owner":"olaviinha","description":"Colabs for text prompt steered image generators","archived":false,"fork":false,"pushed_at":"2024-11-01T20:49:02.000Z","size":267,"stargazers_count":13,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-11-01T21:25:26.533Z","etag":null,"topics":["ai-image","big-sleep","biggan","colab","dall-e","dalle2","google-colab","image-generation","laion","neural-network","neural-networks","openai","rudalle","stable-diffusion","text2image","txt2img","vqgan"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/olaviinha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2021-07-19T12:03:20.000Z","updated_at":"2024-11-01T20:49:05.000Z","dependencies_parsed_at":"2024-05-10T18:44:03.459Z","dependency_job_id":null,"html_url":"https://github.com/olaviinha/NeuralTextToImage","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/olaviinha%2FNeuralTextToImage","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/olaviinha%2FNeuralTextToImage/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/olaviinha%2FNeuralTextToImage/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/olaviinha%2FNeuralTextToImage/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/olaviinha","download_url":"https://codeload.github.com/olaviinha/NeuralTextToImage/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":233828203,"owners_count":18736577,"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":["ai-image","big-sleep","biggan","colab","dall-e","dalle2","google-colab","image-generation","laion","neural-network","neural-networks","openai","rudalle","stable-diffusion","text2image","txt2img","vqgan"],"created_at":"2025-01-14T00:33:22.580Z","updated_at":"2025-09-22T05:32:25.591Z","avatar_url":"https://github.com/olaviinha.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Colab notebooks for text-to-image generators\n\n**❗️ This repository is not maintained since 2022, as closed-source state-of-the-art text-to-image solutions are now widely available for everyone.**\n\nUser-friendly Colab notebooks for various text prompt steered synthetic image generators. These notebooks are not actively maintained, though issues and pull requests are welcome.\n\n**Available notebooks (latest to oldest):**\n\n- [Stable Diffusion](#stable-diffusion-by-compvis-stability-ai-and-laion) (v1.4, v1.5, waifu diffusion)\n- [DALL·E Mini (craiyon.ai)](#dalle-mini-craiyonai-by-boris-dayma)\n- [Latent Diffusion LAION 400M](#latent-diffusion-laion-400m-by-compvis)\n- [ruDALLE Malevich](#rudalle-malevich-by-sberbank-ai)\n- [JAX CLIP Guided Diffusion](#jax-clip-guided-diffusion-by-nshepperd)\n- [CLIP+VQGAN](#clipvqgan-by-katherine-crowson)\n- [Latent Vision](#latent-vision-by-ryan-murdock)\n- [Big Sleep](#big-sleep-by-phil-wang-more-precisely-this-fork)\n\n---\n\nThese techniques are all more or less descendants of Big Sleep (2021), the original concept of turning text into imagery by using [CLIP](https://github.com/openai/CLIP) (OpenAI) to steer [BigGAN](https://arxiv.org/abs/1809.11096) (Andrew Brock et al.), as introduced by [Ryan Murdock](https://github.com/rynmurdock) in his [original notebook](https://colab.research.google.com/drive/1NCceX2mbiKOSlAd_o7IU7nA9UskKN5WR?usp=sharing). The technique has since branched and evolved into what we now know as Midjourney, Dall-E, Stable Diffusion, etc.\n\nI do not use these notebooks on a regular basis, and hence I'm mostly unaware when some library gets updated and a notebook may no longer function; Please do raise an issue should any problems occur.\n\n---\n\n## Stable Diffusion by [CompVis](https://github.com/CompVis), [Stability AI](https://stability.ai) and [LAION](https://laion.ai)\n\nThis colab requires registering with [Hugging Face](https://huggingface.co) for login token and accepting model card terms to download required models [here](https://huggingface.co/CompVis/stable-diffusion-v1-4) and [here](https://huggingface.co/runwayml/stable-diffusion-v1-5).\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/Stable_Diffusion.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/186525426-33e89d0a-e5f1-4f7f-b347-64e3aec567ab.png)\n\n_\"Satanism in the 1900s\"_\n\n---\n\n## DALL·E Mini (craiyon.ai) by [Boris Dayma](https://github.com/borisdayma)\n\nThis colab requires registering with [wandb](https://wandb.ai/) for an authentication key to download required models.\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/dalle_mini.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/179073528-935fe0d2-363e-438b-9706-3e4548dd7569.png)\n\n_\"Satanism in the 1900s\"_\n\n---\n\n## Latent Diffusion LAION 400M by [CompVis](https://github.com/CompVis)\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/LAION_400M.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/163890889-a31370e6-e08d-4389-86af-947fe70a7140.png)\n\n_\"Satanism in the 1900s\"_ (upscaled)\n\n---\n\n## ruDALLE Malevich by [Sberbank-AI](https://github.com/sberbank-ai)\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/ruDalle.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/159492943-572f7a52-83a9-4310-befb-ceb8473af77d.png)\n\u003cbr\u003e\n_\"Satanism in the 1900s\"_\n\n---\n\n## JAX CLIP Guided Diffusion by [nshepperd](https://github.com/nshepperd)\u003cbr\u003e\nMethod originally by [Katherine Crowson](https://github.com/crowsonkb)\u003cbr\u003e\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/JAX_CLIP_Guided_diffusion_nshepperd.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/144711796-3933dbb1-d8a0-4656-812f-050ccb444118.png)\n\u003cbr\u003e\n300 iterations of _\"Satanism in the 1900s\"_.\n\n---\n\n## CLIP+VQGAN by [Katherine Crowson](https://github.com/crowsonkb)\u003cbr\u003e\n**Papers:** 1) [VQGAN by Patrick Esser et al](https://arxiv.org/abs/2012.09841), 2) [CLIP by OpenAI](https://arxiv.org/abs/2103.00020)\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/CLIP%2BVQGAN_crowsonkb.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/126226554-f53ae66d-21d9-428f-9c16-0a17bf8c0ef9.png)\u003cbr\u003e\n400 iterations of _\"Satanism in the 1900s\"_.\n\n---\n\n## Latent Vision by [Ryan Murdock](https://github.com/rynmurdock)\u003cbr\u003e\n**Papers:** 1) [VQGAN by Patrick Esser et al](https://arxiv.org/abs/2012.09841), 2) [CLIP by OpenAI](https://arxiv.org/abs/2103.00020)\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/LatentVision_rynmurdock.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/126967558-b68857b7-0792-4135-b535-687539a3d240.png)\u003cbr\u003e\n400 iterations of _\"Satanism in the 1900s\"_.\n\n---\n\n## Big Sleep by [Phil Wang](https://github.com/lucidrains) (more precisely [this fork](https://github.com/olaviinha/big-sleep))\u003cbr\u003e\n**Papers:** 1) [BigGAN by Andrew Brock et al](https://arxiv.org/abs/1809.11096), 2) [CLIP by OpenAI](https://arxiv.org/abs/2103.00020)\n\nOriginal Big Sleep method.\n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/olaviinha/NeuralTextToImage/blob/main/BigSleep_lucidrains.ipynb?force_theme=dark)\n\n![image](https://user-images.githubusercontent.com/50331907/126226982-815e6fa6-6d5b-4d99-b1b1-902261a88212.png)\u003cbr\u003e\n400 iterations of _\"Satanism in the 1900s\"_.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Folaviinha%2Fneuraltexttoimage","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Folaviinha%2Fneuraltexttoimage","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Folaviinha%2Fneuraltexttoimage/lists"}