Wan 2.2 5B image to video on a 12 GB GPU: ComfyUI setup and offloading caveats

Wan 2.2 5B image-to-video on 12 GB: a documented starting path Start with ComfyUI's native Wan2.2-TI2V-5B workflow. Comfy's documentation, retrieved 2026-10-28, says its 5B path should fit 8 GB with native offloading. That is conditional documentation, not our measurement of this pinned graph on 12 GB. It does not establish simultaneous residency of all files, render speed or remaining VRAM. Use workflow_templates/video_wan2_2_5B_ti2v.json at commit 3c2199b9362457b12b9c60c6cc303501526ebd62. Its model choices match the guide: - models/diffusion_models/wan2.2_ti2v_5B_fp16.safetensors - models/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors - models/vae/wan2.2_vae.safetensors Load the graph, select your start image and enable LoadImage with Ctrl+B. That node is bypassed in the pinned template; leaving it bypassed gives text-only conditioning. Adjust dimensions and frame count in Wan22ImageToVideoLatent. Comfy's guide places prompt editing in CLIP Text Encoder and starts generation with Run or Ctrl/Cmd+Enter. Missing core nodes warrant checking version and startup import errors before seeking third-party replacements. The pinned template's baseline is 1280x704, 121 frames, batch 1; shift 8; 20 steps, CFG 5, uni_pc/simple, denoise 1; output 24 fps. Its seed randomizes. These are saved defaults, not a tested optimal configuration. Record the actual seed, input hash, model hashes/revisions and application/runtime versions for comparisons. Model URLs in the graph track main despite the pinned graph revision. Untested production recommendation: try one subject action and one camera instruction, then vary one setting at a time. Log peak VRAM, system RAM, offloading, dimensions/frames, elapsed time and failures. A successful local run remains required before promising 12 GB performance. Keep the 14B paths separate. The same Comfy page's I2V model list names I2V fp16 files, while its later loading instructions name T2V fp8 files. That is an internal documentation conflict; this answer uses the independently pinned 5B graph and does not resolve the 14B recipe by guessing. Rights: Comfy describes the Wan2.2 series as Apache-2.0; retain applicable notices and inspect the actual downloaded components' terms. This original synthesis includes no weights, images or output media. Shared-founder source review only: source_inspected, not_run, unreviewed. Sources: https://docs.comfy.org/tutorials/video/wan/wan2_2.md and https://raw.githubusercontent.com/Comfy-Org/workflow_templates/3c2199b9362457b12b9c60c6cc303501526ebd62/templates/video_wan2_2_5B_ti2v.json

{
  "citations": [
    {
      "url": "https://docs.comfy.org/tutorials/video/wan/wan2_2.md",
      "note": "comfy-wan22.bin; UTF-8 bytes [4889,5040); excerpt SHA256 e53b268ffe5332b7479d449431cf05a6e024e3d21adfdf4620c7ef51e1b59ef3"
    },
    {
      "url": "https://docs.comfy.org/tutorials/video/wan/wan2_2.md",
      "note": "comfy-wan22.bin; UTF-8 bytes [5706,7921); excerpt SHA256 ebb6d569a3f1d6de251785852d48635e1e074ab03cac694cb94fb93797547aed"
    },
    {
      "url": "https://docs.comfy.org/tutorials/video/wan/wan2_2.md",
      "note": "comfy-wan22.bin; UTF-8 bytes [3828,4694); excerpt SHA256 b670d5dee674106843fd98acbe1372a3ebbb2eb151a00b5ad5516e6db5a9eea2"
    },
    {
      "url": "https://docs.comfy.org/tutorials/video/wan/wan2_2.md",
      "note": "comfy-wan22.bin; UTF-8 bytes [2141,3256); excerpt SHA256 38f4a3d48af88b28bae10473805b21e1f200b52cda5dae106be594190f0a4738"
    },
    {
      "url": "https://docs.comfy.org/tutorials/video/wan/wan2_2.md",
      "note": "comfy-wan22.bin; UTF-8 bytes [11289,15256); excerpt SHA256 a98f79e2a5dde0582104b08d44bb75b87721062f45211e558a7204be0ccd321f"
    },
    {
      "url": "https://raw.githubusercontent.com/Comfy-Org/workflow_templates/3c2199b9362457b12b9c60c6cc303501526ebd62/templates/video_wan2_2_5B_ti2v.json",
      "note": "wan22-template.json; complete JSON; node locators in VIDEO-REVIEW.json; excerpt SHA256 23c93b88adecbdf5bcf4c5438117070fe757f30aca373dd6a2eb488d2c6a585a"
    }
  ]
}