Download Models

ComfyUI needs AI model files to generate images and videos. This guide covers where to download them and where to put them.

If you already downloaded a .safetensors file and only need the right folder, use Where to Put Safetensors in ComfyUI.

Model Types

Where to Download

Hugging Face

The largest open-source model hub. Most official model releases happen here.

• Browse: huggingface.co/models
• Search for models by name and download .safetensors files

If Hugging Face downloads fail with HttpRequestException, MaxRetryError, SSLError, HfHubHTTPError, or LocalEntryNotFoundError, diagnose the download path before reinstalling ComfyUI. See ComfyUI HuggingFace HttpRequestException.

CivitAI

Community-driven platform with thousands of fine-tuned models, LoRAs, and embeddings.

• Browse: civitai.com
• Filter by Type (Checkpoint, LoRA, etc.) and Base Model (SD 1.5, SDXL, Flux)

Recommended Starter Models

For Image Generation

For Video Generation

How to Install

1. Download the .safetensors file (avoid .ckpt files when possible — .safetensors is safer)
2. Place it in the correct subfolder under models/:

ComfyUI/
└── models/
    ├── checkpoints/     ← Main models go here
    ├── loras/           ← LoRA files go here
    ├── vae/             ← VAE files go here
    ├── controlnet/      ← ControlNet models go here
    └── upscale_models/  ← Upscaler models go here

3. Restart ComfyUI (or click Refresh in the model dropdown)

Using GGUF Quantized Models

If you have limited VRAM, you can use GGUF quantized versions of large models (like Flux). These can reduce memory use, but they need GGUF-aware loader nodes and are not normal checkpoints.

Quantized models require the ComfyUI-GGUF custom node. For the full setup path, see ComfyUI GGUF.

1. Install the ComfyUI-GGUF node (see Install Custom Nodes)
2. Download a GGUF version of your model (e.g., flux1-schnell-Q4_K_S.gguf)
3. Place diffusion GGUF files in models/diffusion_models/ or the legacy-compatible models/unet/
4. Use Unet Loader (GGUF) or the loader required by the workflow, not the regular Load Checkpoint node

Tips

• .safetensors vs .ckpt — Always prefer .safetensors. The .ckpt format can contain executable code and is a security risk.
• Hugging Face download errors — If a model URL works in your browser but not in ComfyUI, check proxy, token, gated-repo access, and cache settings before moving files.
• Check the base model — A LoRA trained on SD 1.5 won't work with SDXL checkpoints. Always match the base model.
• Organize subfolders — You can create subfolders inside models/checkpoints/ (e.g., models/checkpoints/sdxl/). ComfyUI scans subdirectories automatically.
• Share models — If you also use A1111 or Forge, configure extra_model_paths.yaml to share model files. See Portable Package setup.
• Check your VRAM — Not sure if a model will run on your GPU? See System Requirements and GPU Compatibility for VRAM guidance.

Next Steps

• Generate your first image
• ComfyUI GGUF
• Where to Put Safetensors in ComfyUI
• ComfyUI HuggingFace HttpRequestException
• Install custom nodes
• Common issues — troubleshooting model loading errors

Source References

• ComfyUI models concept
• ComfyUI model troubleshooting guide
• ComfyUI folder path source
• ComfyUI-GGUF repository