> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# SAM3 video generation model (meta/sam3): where to run it

> SAM3 is a video generation model from Meta. Run it with ComfyUI locally and Comfy Cloud; templates, files, nodes, and pricing.

Model ID: meta/sam3
Provider: meta
Product: local, cloud, workflows, nodes
Input: image, video
Output: video
License: open-weights

SAM3 is a video generation model from Meta. It takes image and video as input and produces video. It has open weights, so you can download the files and run it locally in ComfyUI.

## Where you can run it

| Where | Page | Use it when |
| - | - | - |
| ComfyUI (local or Comfy Cloud) | [SCAIL-2 in ComfyUI: Character Animation and Replacement](https://docs.comfy.org/tutorials/video/zai/scail2.md) | You follow a step-by-step workflow tutorial |
| ComfyUI (local or Comfy Cloud) | [SAM 3.1 in ComfyUI: Segment Anything in Images and Videos](https://docs.comfy.org/tutorials/utility/video-segment-sam3.md) | You follow a step-by-step workflow tutorial |
| ComfyUI (local or Comfy Cloud) | [SAM 3D Body: Extract 3D Human Mesh From Video in ComfyUI](https://docs.comfy.org/tutorials/utility/sam3d-body.md) | You follow a step-by-step workflow tutorial |
| ComfyUI (local or Comfy Cloud) | [VOID: Video Inpainting in ComfyUI](https://docs.comfy.org/tutorials/utility/void-video-inpainting.md) | You follow a step-by-step workflow tutorial |
| Comfy Cloud | [Open `utility_void_video_inpainting` on Comfy Cloud](https://cloud.comfy.org/?template=utility_void_video_inpainting) | You want to run a ready-made workflow without installing anything |

## Model files for running it locally

Put each file in the matching folder under `ComfyUI/models/`. These come from the workflow templates below (workflow\_templates at `3c2199b9`).

| File | Folder | Download |
| - | - | - |
| `sam3.1_multiplex_fp16.safetensors` | `models/checkpoints/` | [Download](https://huggingface.co/Comfy-Org/sam3.1/resolve/main/checkpoints/sam3.1_multiplex_fp16.safetensors) |
| `void_pass2.safetensors` | `models/diffusion_models/` | [Download](https://huggingface.co/Comfy-Org/void-model/resolve/main/diffusion_models/void_pass2.safetensors) |
| `void_pass1.safetensors` | `models/diffusion_models/` | [Download](https://huggingface.co/Comfy-Org/void-model/resolve/main/diffusion_models/void_pass1.safetensors) |
| `raft_large_C_T_SKHT_V2-ff5fadd5.safetensors` | `models/optical_flow/` | [Download](https://huggingface.co/Comfy-Org/void-model/resolve/main/optical_flow/raft_large_C_T_SKHT_V2-ff5fadd5.safetensors) |
| `t5xxl_fp16.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp16.safetensors) |
| `cogvideox_vae.safetensors` | `models/vae/` | [Download](https://huggingface.co/Comfy-Org/void-model/resolve/main/vae/cogvideox_vae.safetensors) |

## Workflow templates

| Template | Title | Added |
| - | - | - |
| `utility_void_video_inpainting` | Video Inpainting: VOID | 2026-05-14 |
| `utility_video_segment_sam3` | Video Segmentation: SAM3 | 2026-04-27 |
| `utility_image_segment_sam3` | Image Segmentation: SAM3 | 2026-04-26 |
| `utility_sam3d_body` | SAM 3D Body: 3D Human Mesh Extraction From Video | 2026-08-25 |
| `video_wan21_scail2_character_replacement_int8` | SCAIL-2 Int8: Character Replacement | 2026-07-13 |
| `video_wan21_scail2_character_replacement` | SCAIL-2: Character Replacement | 2026-06-15 |
| `templates_shane_change_any_objects` | Change Any Objects | 2026-03-04 |
| `video_wan_vace_inpainting` | Wan2.1 VACE Inpainting | 2025-05-21 |

## Nodes

* [SAM3\_Detect](https://docs.comfy.org/built-in-nodes/SAM3_Detect.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.