[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1829":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":42,"readmeContent":43,"aiSummary":44,"trendingCount":16,"starSnapshotCount":16,"syncStatus":45,"lastSyncTime":46,"discoverSource":47},1829,"diffusers","huggingface\u002Fdiffusers","huggingface","🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.","https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers",null,"Python",33827,7041,215,725,0,6,56,232,36,112,"Apache License 2.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"deep-learning","diffusion","flux","image-generation","image2image","image2video","latent-diffusion-models","pytorch","qwen-image","score-based-generative-modeling","stable-diffusion","stable-diffusion-diffusers","text2image","text2video","video2video","2026-06-12 04:00:11","\u003C!---\nCopyright 2022 - The HuggingFace Team. All rights reserved.\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\n    http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.\n-->\n\n\u003Cp align=\"center\">\n    \u003Cbr>\n    \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fhuggingface\u002Fdiffusers\u002Fmain\u002Fdocs\u002Fsource\u002Fen\u002Fimgs\u002Fdiffusers_library.jpg\" width=\"400\"\u002F>\n    \u003Cbr>\n\u003Cp>\n\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg alt=\"GitHub\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fhuggingface\u002Fdatasets.svg?color=blue\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Freleases\">\u003Cimg alt=\"GitHub release\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Frelease\u002Fhuggingface\u002Fdiffusers.svg\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fpepy.tech\u002Fproject\u002Fdiffusers\">\u003Cimg alt=\"GitHub release\" src=\"https:\u002F\u002Fstatic.pepy.tech\u002Fbadge\u002Fdiffusers\u002Fmonth\">\u003C\u002Fa>\n    \u003Ca href=\"CODE_OF_CONDUCT.md\">\u003Cimg alt=\"Contributor Covenant\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContributor%20Covenant-2.1-4baaaa.svg\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Ftwitter.com\u002Fdiffuserslib\">\u003Cimg alt=\"X account\" src=\"https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Furl\u002Fhttps\u002Ftwitter.com\u002Fdiffuserslib.svg?style=social&label=Follow%20%40diffuserslib\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n🤗 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, 🤗 Diffusers is a modular toolbox that supports both. Our library is designed with a focus on [usability over performance](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fconceptual\u002Fphilosophy#usability-over-performance), [simple over easy](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fconceptual\u002Fphilosophy#simple-over-easy), and [customizability over abstractions](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fconceptual\u002Fphilosophy#tweakable-contributorfriendly-over-abstraction).\n\n🤗 Diffusers offers three core components:\n\n- State-of-the-art [diffusion pipelines](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Foverview) that can be run in inference with just a few lines of code.\n- Interchangeable noise [schedulers](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fschedulers\u002Foverview) for different diffusion speeds and output quality.\n- Pretrained [models](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fmodels\u002Foverview) that can be used as building blocks, and combined with schedulers, for creating your own end-to-end diffusion systems.\n\n## Installation\n\nWe recommend installing 🤗 Diffusers in a virtual environment from PyPI or Conda. For more details about installing [PyTorch](https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F), please refer to their official documentation.\n\n### PyTorch\n\nWith `pip` (official package):\n\n```bash\npip install --upgrade diffusers[torch]\n```\n\nWith `conda` (maintained by the community):\n\n```sh\nconda install -c conda-forge diffusers\n```\n\n### Apple Silicon (M1\u002FM2) support\n\nPlease refer to the [How to use Stable Diffusion in Apple Silicon](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Foptimization\u002Fmps) guide.\n\n## Quickstart\n\nGenerating outputs is super easy with 🤗 Diffusers. To generate an image from text, use the `from_pretrained` method to load any pretrained diffusion model (browse the [Hub](https:\u002F\u002Fhuggingface.co\u002Fmodels?library=diffusers&sort=downloads) for 30,000+ checkpoints):\n\n```python\nfrom diffusers import DiffusionPipeline\nimport torch\n\npipeline = DiffusionPipeline.from_pretrained(\"stable-diffusion-v1-5\u002Fstable-diffusion-v1-5\", torch_dtype=torch.float16)\npipeline.to(\"cuda\")\npipeline(\"An image of a squirrel in Picasso style\").images[0]\n```\n\nYou can also dig into the models and schedulers toolbox to build your own diffusion system:\n\n```python\nfrom diffusers import DDPMScheduler, UNet2DModel\nfrom PIL import Image\nimport torch\n\nscheduler = DDPMScheduler.from_pretrained(\"google\u002Fddpm-cat-256\")\nmodel = UNet2DModel.from_pretrained(\"google\u002Fddpm-cat-256\").to(\"cuda\")\nscheduler.set_timesteps(50)\n\nsample_size = model.config.sample_size\nnoise = torch.randn((1, 3, sample_size, sample_size), device=\"cuda\")\ninput = noise\n\nfor t in scheduler.timesteps:\n    with torch.no_grad():\n        noisy_residual = model(input, t).sample\n        prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample\n        input = prev_noisy_sample\n\nimage = (input \u002F 2 + 0.5).clamp(0, 1)\nimage = image.cpu().permute(0, 2, 3, 1).numpy()[0]\nimage = Image.fromarray((image * 255).round().astype(\"uint8\"))\nimage\n```\n\nCheck out the [Quickstart](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fquicktour) to launch your diffusion journey today!\n\n## How to navigate the documentation\n\n| **Documentation**                                                   | **What can I learn?**                                                                                                                                                                           |\n|---------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [Tutorial](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Ftutorials\u002Ftutorial_overview)                                                            | A basic crash course for learning how to use the library's most important features like using models and schedulers to build your own diffusion system, and training your own diffusion model.  |\n| [Loading](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fusing-diffusers\u002Floading)                                                             | Guides for how to load and configure all the components (pipelines, models, and schedulers) of the library, as well as how to use different schedulers.                                         |\n| [Pipelines for inference](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fusing-diffusers\u002Foverview_techniques)                                             | Guides for how to use pipelines for different inference tasks, batched generation, controlling generated outputs and randomness, and how to contribute a pipeline to the library.               |\n| [Optimization](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Foptimization\u002Ffp16)                                                        | Guides for how to optimize your diffusion model to run faster and consume less memory.                                                                                                          |\n| [Training](https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Ftraining\u002Foverview) | Guides for how to train a diffusion model for different tasks with different training techniques.                                                                                               |\n## Contribution\n\nWe ❤️  contributions from the open-source community!\nIf you want to contribute to this library, please check out our [Contribution guide](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Fblob\u002Fmain\u002FCONTRIBUTING.md).\nYou can look out for [issues](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Fissues) you'd like to tackle to contribute to the library.\n- See [Good first issues](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Fissues?q=is%3Aopen+is%3Aissue+label%3A%22good+first+issue%22) for general opportunities to contribute\n- See [New model\u002Fpipeline](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Fissues?q=is%3Aopen+is%3Aissue+label%3A%22New+pipeline%2Fmodel%22) to contribute exciting new diffusion models \u002F diffusion pipelines\n- See [New scheduler](https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers\u002Fissues?q=is%3Aopen+is%3Aissue+label%3A%22New+scheduler%22)\n\nAlso, say 👋 in our public Discord channel \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FG7tWnz98XR\">\u003Cimg alt=\"Join us on Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F823813159592001537?color=5865F2&logo=discord&logoColor=white\">\u003C\u002Fa>. We discuss the hottest trends about diffusion models, help each other with contributions, personal projects or just hang out ☕.\n\n\n## Popular Tasks & Pipelines\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Cth>Task\u003C\u002Fth>\n    \u003Cth>Pipeline\u003C\u002Fth>\n    \u003Cth>🤗 Hub\u003C\u002Fth>\n  \u003C\u002Ftr>\n  \u003Ctr style=\"border-top: 2px solid black\">\n    \u003Ctd>Unconditional Image Generation\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fddpm\"> DDPM \u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fgoogle\u002Fddpm-ema-church-256\"> google\u002Fddpm-ema-church-256 \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr style=\"border-top: 2px solid black\">\n    \u003Ctd>Text-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fstable_diffusion\u002Ftext2img\">Stable Diffusion Text-to-Image\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fstable-diffusion-v1-5\u002Fstable-diffusion-v1-5\"> stable-diffusion-v1-5\u002Fstable-diffusion-v1-5 \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>Text-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Funclip\">unCLIP\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fkakaobrain\u002Fkarlo-v1-alpha\"> kakaobrain\u002Fkarlo-v1-alpha \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>Text-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fdeepfloyd_if\">DeepFloyd IF\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FDeepFloyd\u002FIF-I-XL-v1.0\"> DeepFloyd\u002FIF-I-XL-v1.0 \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>Text-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fkandinsky\">Kandinsky\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fkandinsky-community\u002Fkandinsky-2-2-decoder\"> kandinsky-community\u002Fkandinsky-2-2-decoder \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr style=\"border-top: 2px solid black\">\n    \u003Ctd>Text-guided Image-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fcontrolnet\">ControlNet\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Flllyasviel\u002Fsd-controlnet-canny\"> lllyasviel\u002Fsd-controlnet-canny \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>Text-guided Image-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fpix2pix\">InstructPix2Pix\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Ftimbrooks\u002Finstruct-pix2pix\"> timbrooks\u002Finstruct-pix2pix \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>Text-guided Image-to-Image\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fstable_diffusion\u002Fimg2img\">Stable Diffusion Image-to-Image\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fstable-diffusion-v1-5\u002Fstable-diffusion-v1-5\"> stable-diffusion-v1-5\u002Fstable-diffusion-v1-5 \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr style=\"border-top: 2px solid black\">\n    \u003Ctd>Text-guided Image Inpainting\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fstable_diffusion\u002Finpaint\">Stable Diffusion Inpainting\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fstable-diffusion-v1-5\u002Fstable-diffusion-inpainting\"> stable-diffusion-v1-5\u002Fstable-diffusion-inpainting \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr style=\"border-top: 2px solid black\">\n    \u003Ctd>Image Variation\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fstable_diffusion\u002Fimage_variation\">Stable Diffusion Image Variation\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Flambdalabs\u002Fsd-image-variations-diffusers\"> lambdalabs\u002Fsd-image-variations-diffusers \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr style=\"border-top: 2px solid black\">\n    \u003Ctd>Super Resolution\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fstable_diffusion\u002Fupscale\">Stable Diffusion Upscale\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fstabilityai\u002Fstable-diffusion-x4-upscaler\"> stabilityai\u002Fstable-diffusion-x4-upscaler \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd>Super Resolution\u003C\u002Ftd>\n    \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fdocs\u002Fdiffusers\u002Fapi\u002Fpipelines\u002Fstable_diffusion\u002Flatent_upscale\">Stable Diffusion Latent Upscale\u003C\u002Fa>\u003C\u002Ftd>\n      \u003Ctd>\u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fstabilityai\u002Fsd-x2-latent-upscaler\"> stabilityai\u002Fsd-x2-latent-upscaler \u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n## Popular libraries using 🧨 Diffusers\n\n- https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FTaskMatrix\n- https:\u002F\u002Fgithub.com\u002Finvoke-ai\u002FInvokeAI\n- https:\u002F\u002Fgithub.com\u002FInstantID\u002FInstantID\n- https:\u002F\u002Fgithub.com\u002Fapple\u002Fml-stable-diffusion\n- https:\u002F\u002Fgithub.com\u002FSanster\u002Flama-cleaner\n- https:\u002F\u002Fgithub.com\u002FIDEA-Research\u002FGrounded-Segment-Anything\n- https:\u002F\u002Fgithub.com\u002Fashawkey\u002Fstable-dreamfusion\n- https:\u002F\u002Fgithub.com\u002Fdeep-floyd\u002FIF\n- https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\n- https:\u002F\u002Fgithub.com\u002Fbmaltais\u002Fkohya_ss\n- +14,000 other amazing GitHub repositories 💪\n\nThank you for using us ❤️.\n\n## Credits\n\nThis library concretizes previous work by many different authors and would not have been possible without their great research and implementations. We'd like to thank, in particular, the following implementations which have helped us in our development and without which the API could not have been as polished today:\n\n- @CompVis' latent diffusion models library, available [here](https:\u002F\u002Fgithub.com\u002FCompVis\u002Flatent-diffusion)\n- @hojonathanho original DDPM implementation, available [here](https:\u002F\u002Fgithub.com\u002Fhojonathanho\u002Fdiffusion) as well as the extremely useful translation into PyTorch by @pesser, available [here](https:\u002F\u002Fgithub.com\u002Fpesser\u002Fpytorch_diffusion)\n- @ermongroup's DDIM implementation, available [here](https:\u002F\u002Fgithub.com\u002Fermongroup\u002Fddim)\n- @yang-song's Score-VE and Score-VP implementations, available [here](https:\u002F\u002Fgithub.com\u002Fyang-song\u002Fscore_sde_pytorch)\n\nWe also want to thank @heejkoo for the very helpful overview of papers, code and resources on diffusion models, available [here](https:\u002F\u002Fgithub.com\u002Fheejkoo\u002FAwesome-Diffusion-Models) as well as @crowsonkb and @rromb for useful discussions and insights.\n\n## Citation\n\n```bibtex\n@misc{von-platen-etal-2022-diffusers,\n  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Dhruv Nair and Sayak Paul and William Berman and Yiyi Xu and Steven Liu and Thomas Wolf},\n  title = {Diffusers: State-of-the-art diffusion models},\n  year = {2022},\n  publisher = {GitHub},\n  journal = {GitHub repository},\n  howpublished = {\\url{https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fdiffusers}}\n}\n```\n","🤗 Diffusers 是一个用于生成图像、音频甚至分子3D结构的最先进预训练扩散模型库。该项目的核心功能包括易于使用的扩散管道、可互换的噪声调度器以及作为构建块的预训练模型，这些组件可以灵活组合以创建自定义的端到端扩散系统。Diffusers 采用 PyTorch 构建，强调易用性、简洁性和高度可定制化的设计哲学。此项目非常适合需要高质量多媒体内容生成的应用场景，如创意艺术设计、虚拟现实环境构建或科学研究中的分子模拟等。",2,"2026-06-11 02:46:16","top_all"]