Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Run compatible language models locally; explicitly distinguish local models from optional cloud models.
Platforms
Windows · macOS · Linux
Guidance & sources
Start with a small local model and check whether cloud functionality is enabled.
Disable optional cloud features when you require a local-only workflow. Model licenses are separate.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Explore a graphical workflow for downloading and running compatible local language models.
Platforms
Windows · macOS · Linux
Guidance & sources
Check the model, runtime compatibility and your device memory before a large download.
Edition and requirements can change; check the official source before installing.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Build node-based image generation, image processing and supported video workflows.
Platforms
Windows · macOS · Linux
Guidance & sources
Capabilities depend on installed models, custom nodes and workflows; ComfyUI alone is not a video generator. Local core is free; optional cloud/partner nodes may cost money. Stable Diffusion model licenses differ.
Edition and requirements can change; check the official source before installing.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Draft, explain and research through conversation; review generated answers before using them.
Platforms
Web
Guidance & sources
Useful for drafting and explanations; independently verify factual and coding output.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Explore an assistant for writing, reasoning and coding with the context you supply.
Platforms
Web
Guidance & sources
Use for text and coding assistance with your own tests and source checks.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Explore Google’s assistant for everyday questions and work with supported connected services.
Platforms
Web
Guidance & sources
Evaluate research and drafting output against the underlying sources.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Compare another general assistant using the same task and independently check its output.
Platforms
Web
Guidance & sources
Check sources and dates for answers that discuss recent events.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Explore a conversational AI service; distinguish the hosted service from separately licensed model releases.
Platforms
Web
Guidance & sources
Distinguish the hosted service from separately licensed downloadable models.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Explore generative image workflows; check credits, output rights and available features for your plan.
Platforms
Web
Guidance & sources
Check the selected feature and output-use terms before a commercial project.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Explore generative video workflows; compare a short test before committing to a paid workflow.
Platforms
Web
Guidance & sources
Try short clips first and check available credits and export requirements.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Explore AI music creation; check the applicable plan and rights before publishing outputs.
Platforms
Web
Guidance & sources
Check music-use rights for the actual plan and intended publication.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Build local image-generation and canvas workflows with supported models.
Platforms
Windows · macOS · Linux
Guidance & sources
Model licenses, hardware and supported workflows differ. Stable Diffusion is a model family, not a single universally licensed app.
Edition and requirements can change; check the official source before installing.
Choose by medium: GIMP for raster editing, Krita for painting, Inkscape for vectors, Blender for 3D and ShareX for Windows capture. Keep editable source files and export a separate delivery copy. Advanced creative work takes practice; begin with one small project.
Chat with supported local language models or optional remote providers.
Platforms
Windows · macOS · Linux
Guidance & sources
Download a compatible model and check RAM/GPU and its license. Local mode can work offline after downloads; enabling remote providers changes data processing and may cost money.
Edition and requirements can change; check the official source before installing.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Run supported language models locally and explore local document chat.
Platforms
Windows · macOS · Linux
Guidance & sources
Download a compatible model and check RAM/GPU and its license. Local mode can work offline after downloads; enabling remote providers changes data processing and may cost money.
Edition and requirements can change; check the official source before installing.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Self-host a web interface for local or remote model providers.
Platforms
Self-hosted server · Web
Guidance & sources
Current source license imposes a branding condition; do not classify it as unrestricted open source. Model/provider licenses and remote processing are separate; self-hosting needs administration.
Edition and requirements can change; check the official source before installing.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Transcribe supported audio locally with multilingual speech-recognition models.
Platforms
Windows · macOS · Linux
Guidance & sources
Download a compatible model and check RAM/GPU and its license. Local mode can work offline after downloads; enabling remote providers changes data processing and may cost money.
Edition and requirements can change; check the official source before installing.
Local AI runs model inference on your own device. After downloading software and models, supported local workflows can work offline; cloud features and extensions may still send data. RAM is system memory, VRAM is GPU memory. CPUs can run some models more slowly; a compatible GPU can accelerate supported workloads. Larger models require more memory. Quantization uses fewer bits to reduce size, trading some accuracy for easier running. Start small, check model licenses and measure on your actual machine.
Explore AI-assisted web research with linked sources.
Platforms
Web · iOS · Android
Guidance & sources
Free access has service limits and may change. Requests are processed by the provider; verify sources and never assume an AI answer is correct.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
Try hosted conversations with models offered by Hugging Face.
Platforms
Web
Guidance & sources
Free access has service limits and may change. Requests are processed by the provider; verify sources and never assume an AI answer is correct.
Edition and requirements can change; check the official source before installing.
Choose a capability before a brand: general conversation, coding, research, images, video or music. Compare tools on the same task and verify sources and outputs. Hosted services process data under provider terms; plans, limits and features change. Do not upload confidential business material without an appropriate policy.
EN
NL
FR
DE
TR
