{"id":13561939,"url":"https://github.com/kabachuha/sd-webui-text2video","last_synced_at":"2025-04-08T04:15:04.169Z","repository":{"id":143586667,"uuid":"616179530","full_name":"kabachuha/sd-webui-text2video","owner":"kabachuha","description":"Auto1111 extension implementing text2video diffusion models (like ModelScope or VideoCrafter) using only Auto1111 webui dependencies","archived":false,"fork":false,"pushed_at":"2024-07-14T07:14:03.000Z","size":817,"stargazers_count":1312,"open_issues_count":49,"forks_count":111,"subscribers_count":26,"default_branch":"main","last_synced_at":"2025-04-01T03:35:22.085Z","etag":null,"topics":["automatic1111","extension","gradio","modelscope","stable-diffusion","text2video","videocrafter","webui"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kabachuha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","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},"funding":{"github":null,"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":["https://etherscan.io/address/0x4c92637b8d3587383d50812f64a0dbd2a5426e81"]}},"created_at":"2023-03-19T20:40:23.000Z","updated_at":"2025-03-26T17:16:11.000Z","dependencies_parsed_at":"2024-09-25T00:07:14.071Z","dependency_job_id":"371a752e-b101-46e6-bb4d-25612908dd8c","html_url":"https://github.com/kabachuha/sd-webui-text2video","commit_stats":null,"previous_names":["kabachuha/sd-webui-text2video","deforum-art/sd-webui-text2video"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kabachuha%2Fsd-webui-text2video","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kabachuha%2Fsd-webui-text2video/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kabachuha%2Fsd-webui-text2video/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kabachuha%2Fsd-webui-text2video/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kabachuha","download_url":"https://codeload.github.com/kabachuha/sd-webui-text2video/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247773719,"owners_count":20993639,"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":["automatic1111","extension","gradio","modelscope","stable-diffusion","text2video","videocrafter","webui"],"created_at":"2024-08-01T13:01:02.804Z","updated_at":"2025-04-08T04:15:04.126Z","avatar_url":"https://github.com/kabachuha.png","language":"Python","funding_links":["https://etherscan.io/address/0x4c92637b8d3587383d50812f64a0dbd2a5426e81"],"categories":["Python","GitHub projects","HarmonyOS","视频生成_补帧_摘要"],"sub_categories":["Windows Manager","资源传输下载"],"readme":"# text2video Extension for AUTOMATIC1111's StableDiffusion WebUI\n\n**~~Warning: as of 2023-11-21 this extension is not maintained. If you'd like to continue devving/remaking it, please contact me on Discord @kabachuha (you can also find me on [camenduru's server's text2video channel](https://discord.gg/TYk6rfT9)) and we'll figure it out~~**\n\n**~~Maintained starting on 2023-11-21 by [Deforum-art](https://github.com/deforum-art)~~**\n\n**Maintained by me again**\n\nAuto1111 extension implementing various text2video models, such as ModelScope and VideoCrafter, using only Auto1111 webui dependencies and downloadable models (so no logins required anywhere)\n\n## Requirements\n\n### ModelScope\n\n6 GBs vram should be enough to run on GPU with low vram vae on at 256x256 (and we are already getting reports of people launching 192x192 videos [with 4gbs of vram](https://github.com/deforum-art/sd-webui-modelscope-text2video/discussions/27)). 24 frames long 256x256 video definitely fits into 12gbs of NVIDIA GeForce RTX 2080 Ti, or if you have a Torch2 attention optimization supported videocard, you can fit the whopping 125 frames (8 seconds) long video into the same 12 GBs of VRAM! 250 frames (16 seconds) in the same conditions take 20 gbs.\n\nPrompt: `best quality, anime girl dancing`\n\nhttps://user-images.githubusercontent.com/14872007/232229730-82df36cc-ac8b-46b3-949d-0e1dfc10a975.mp4\n\n\nWe will appreciate *any* help with this extension, *especially* pull-requests.\n\n### LoRA Support\n\nCurrently, there is support for trained LoRAs using this finetune repository. Please follow instructions there on how to train them.\nhttps://github.com/ExponentialML/Text-To-Video-Finetuning#updates\n\nAfter training, simply place them into your default LoRA directory defined by your webui installation.\n\n### VideoCrafter (WIP, needs more devs to maintain properly as well)\n\nVideoCrafter runs with around 9.2 GBs of VRAM with the settings set on Default.\n\n## Major changes between versions\n\nUpdate 2023-03-27: VAE settings and \"Keep model in VRAM\" moved to general webui setting under 'ModelScopeTxt2Vid' section. \n\nUpdate 2023-03-26: prompt weights **implemented**! (ModelScope only yet, as of 2023-04-05)\n\nUpdate 2023-04-05: added VideoCrafter support, renamed the extension to plainly 'sd-webui-text2video'\n\nUpdate 2023-04-13: in-framing/in-painting support: allows to 'animate' an existing pic or even seamlessly loop the videos! \n\nUpdate 2023-04-15: **MEGA-UPDATE**: Torch2/xformers optimizations, possible to make 125 frames long video on 12 gbs of VRAM. CPU offloading doesn't happen now if keep_pipe_in_vram is checked.\n\nUpdate 2023-04-16: WebAPI is available!\n\nUpdate 2023-07-02: Alternate samplers, model hotswitch.\n\n## Test examples:\n\n### ModelScope\n\nPrompt: `cinematic explosion by greg rutkowski`\n\nhttps://user-images.githubusercontent.com/14872007/226345611-a1f0601f-db32-41bd-b983-80d363eca4d5.mp4\n\nPrompt: `really attractive anime girl skating, by makoto shinkai, cinematic lighting`\n\nhttps://user-images.githubusercontent.com/14872007/226468406-ce43fa0c-35f2-4625-a892-9fb3411d96bb.mp4\n\n**'Continuing' an existing image**\n\nPrompt: `best quality, astronaut dog`\n\nhttps://user-images.githubusercontent.com/14872007/232073361-bdb87a47-85ec-44d8-9dc4-40dab0bd0555.mp4\n\nPrompt: `explosion`\n\nhttps://user-images.githubusercontent.com/14872007/232073687-b7e78b06-182b-4ce6-b565-d6738c4890d1.mp4\n\n**In-painting and looping back the videos**\n\nPrompt: `nuclear explosion`\n\nhttps://user-images.githubusercontent.com/14872007/232073842-84860a3e-fa82-43a6-a411-5cfc509b5355.mp4\n\nPrompt: `best quality, lots of cheese`\n\nhttps://user-images.githubusercontent.com/14872007/232073876-16895cae-0f26-41bc-a575-0c811219cf88.mp4\n\n### VideoCrafter\n\nPrompt: `anime 1girl reimu touhou`\n\nhttps://user-images.githubusercontent.com/14872007/230231253-2fd9b7af-3f05-41c8-8c92-51042b269116.mp4\n\n## Where to get the weights\n\n### ModelScope\n\nDownload the following files from the [original HuggingFace repository](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis/tree/main). Alternatively, [download half-precision fp16 pruned weights (they are smaller and use less vram on loading)](https://huggingface.co/kabachuha/modelscope-damo-text2video-pruned-weights/tree/main):\n- VQGAN_autoencoder.pth\n- configuration.json\n- open_clip_pytorch_model.bin\n- text2video_pytorch_model.pth\n\nAnd put them in `stable-diffusion-webui/models/ModelScope/t2v`. Create those 2 folders if they are missing. \n\n### VideoCrafter\n\nDownload pretrained T2V models either via [this link](https://drive.google.com/file/d/13ZZTXyAKM3x0tObRQOQWdtnrI2ARWYf_/view?usp=share_link) or download [the pruned half precision weights](https://huggingface.co/kabachuha/videocrafter-pruned-weights/tree/main), and put the `model.ckpt` in `models/VideoCrafter/model.ckpt`.\n\n## Fine-tunes and how to use them\n\nThanks to https://github.com/ExponentialML/Text-To-Video-Finetuning you can fine-tune your models!\n\nTo utilize a fine-tuned model here, use [this script](https://github.com/ExponentialML/Text-To-Video-Finetuning/pull/52) which will convert the Diffusers-formatted model that repo outputs into the original weights format.\n\n### Prominent Fine-tunes\n\n**ZeroScope v2**\n\nTrained by @cerspense on high quality YouTube videos. Download the files from the folder named `zs2_XL` at [cerspense/zeroscope_v2_XL](https://huggingface.co/cerspense/zeroscope_v2_XL/tree/main/zs2_XL) and then add the missing `VQGAN_autoencoder.pth` and `configuration.json` from [any other ModelScope model](https://huggingface.co/kabachuha/modelscope-damo-text2video-pruned-weights/tree/main).\n\nhttps://github.com/kabachuha/sd-webui-text2video/assets/14872007/6fa39221-3608-415e-b8ce-04a2bad11d30\n\n**Potat1**\n\n[Potat1](https://huggingface.co/camenduru/potat1) is a ModelScope-based model trained by @camenduru on 2197 clips with the resolution of 1024x576 which makes it the first open source hi-res text2video model. \n\nhttps://github.com/kabachuha/sd-webui-text2video/assets/14872007/ff01c6cb-0000-40a2-ac7e-ec3edc5f9713\n\nTo download the plug-and-play weights for the extension use this link https://huggingface.co/kabachuha/potat1-with-text-encoder-original-format.\n\n**Animov-0.1**\n\n[Animov-0.1 by strangeman3107](https://huggingface.co/datasets/strangeman3107/animov-0.1). The converted weights for this model reside [here](https://huggingface.co/kabachuha/animov-0.1-modelscope-original-format).\n\nhttps://user-images.githubusercontent.com/14872007/232611542-600cec38-d944-4530-bc5c-3595a115c2be.mp4\n\n## Screenshots\n\ntxt2vid with img2vid\n\n![Screenshot 2023-04-15 at 17-53-36 Stable Diffusion](https://user-images.githubusercontent.com/14872007/232232319-c3a443ee-1a8a-4504-a114-d9da2ae916c2.png)\n\nvid2vid\n\n![Screenshot 2023-04-15 at 17-33-32 Stable Diffusion](https://user-images.githubusercontent.com/14872007/232232338-a2aa4b78-35d0-4c9b-850b-15edc90c0c9f.png)\n\n## Dev resources\n\n### ModelScope\n\nHuggingFace space:\n\nhttps://huggingface.co/spaces/damo-vilab/modelscope-text-to-video-synthesis\n\nThe model PyTorch implementation from ModelScope:\n\nhttps://github.com/modelscope/modelscope/tree/master/modelscope/models/multi_modal/video_synthesis\n\nGoogle Colab from the devs:\n\nhttps://colab.research.google.com/drive/1uW1ZqswkQ9Z9bp5Nbo5z59cAn7I0hE6R?usp=sharing\n\n### VideoCrafter\n\nGithub:\n\nhttps://github.com/VideoCrafter/VideoCrafter\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkabachuha%2Fsd-webui-text2video","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkabachuha%2Fsd-webui-text2video","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkabachuha%2Fsd-webui-text2video/lists"}