工作流 / 视频 / PixVerse V6 Max：文生视频
PixVerse V6 Max：文生视频

PixVerse V6 Max: Text to Video
使用 PixVerse V6 Max，通过文本提示词生成最长 15 秒、1080p 的视频。PixVerse V6 Max 是 PixVerse V6 的高保真版本，可在单次生成中实现原生音频和多镜头调度。无需输入文件。非常适合社交广告、产品概念短片和短篇故事叙述。
视频 3 个节点 17 次使用 ComfyUI ≥ 0.42.5 ComfyUI 7 KB
下载工作流 JSON 查看官方来源
下载后把文件拖进 ComfyUI 窗口即可打开。
节点构成

MarkdownNote × 1
PixverseV6TextToVideoNode × 1
SaveVideo × 1
官方标注的模型

PixVerse
工作流 JSON

和上面「下载工作流 JSON」是同一份文件。
1{
  "id": "099c8464-dbd3-4bb0-b8c2-7f9a45d78014",
  "revision": 0,
  "last_node_id": 3,
  "last_link_id": 1,
  "nodes": [
      {
          "id": 2,
          "type": "MarkdownNote",
          "pos": [
              40,
              40
          ],
          "size": [
              420,
              500
          ],
          "flags": [],
          "order": 0,
          "mode": 0,
          "inputs": [],
          "outputs": [],
          "properties": [],
          "widgets_values": [
              "# PixVerse V6 Max: Text to Video\n\nDescribe the shot and PixVerse V6 Max renders a single clip with optional native audio, from 360p to 1080p and up to 15 seconds, with no input files required.\n\n## Parameters\n\n- `quality` sets the long edge: 360p is 640 px, 540p 1024 px, 720p 1280 px and 1080p 1920 px.\n- `multi_clip` lets the model cut the video into several shots instead of one continuous take.\n- `negative_prompt` is the only optional text field on V6 Max; the style presets that PixVerse V6 offers are not part of this tier.\n- PixVerse records the seed but does not reproduce a run from it.\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
          ],
          "widgets_values_named": {
              "text": "# PixVerse V6 Max: Text to Video\n\nDescribe the shot and PixVerse V6 Max renders a single clip with optional native audio, from 360p to 1080p and up to 15 seconds, with no input files required.\n\n## Parameters\n\n- `quality` sets the long edge: 360p is 640 px, 540p 1024 px, 720p 1280 px and 1080p 1920 px.\n- `multi_clip` lets the model cut the video into several shots instead of one continuous take.\n- `negative_prompt` is the only optional text field on V6 Max; the style presets that PixVerse V6 offers are not part of this tier.\n- PixVerse records the seed but does not reproduce a run from it.\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
          },
          "color": "#222",
          "bgcolor": "#000"
      },
      {
          "id": 1,
          "type": "PixverseV6TextToVideoNode",
          "pos": [
              500,
              40
          ],
          "size": [
              420,
              460
          ],
          "flags": [],
          "order": 1,
          "mode": 0,
          "inputs": [],
          "outputs": [
              {
                  "name": "VIDEO",
                  "type": "VIDEO",
                  "links": [
                      1
                  ]
              }
          ],
          "properties": {
              "Node name for S&R": "PixverseV6TextToVideoNode"
          },
          "widgets_values": [
              "PixVerse V6 Max",
              "Product advertising film for a light grey knit running shoe, three shots. Shot one: side silhouette from a 45 degree angle, camera tracks slowly sideways, seamless light grey gradient backdrop, hard specular highlight on the knit upper, macro depth of field. Shot two: extreme close up of the sole tread pattern, a hard light sweeps from the left across the rubber surface revealing the groove geometry. Shot three: the shoe descends from above into frame and lands on a matte pale stone plinth, a few fine dust particles lift gently at the instant of contact, generous negative space. Seamless gradient backdrop, hard specular light, shallow depth of field, restrained palette, no text, no logo, no people.",
              "16:9",
              "720p",
              10,
              true,
              false,
              2081797219,
              "randomize",
              "text, letters, words, typography, watermark, logo, brand mark, UI, screen content, subtitles, caption, people, hands, human, cartoon, illustration, oversaturated colors, lens flare artifacts, chroma noise, watermark border, clutter",
              "randomize"
          ],
          "widgets_values_named": {
              "model": "PixVerse V6 Max",
              "model.prompt": "Product advertising film for a light grey knit running shoe, three shots. Shot one: side silhouette from a 45 degree angle, camera tracks slowly sideways, seamless light grey gradient backdrop, hard specular highlight on the knit upper, macro depth of field. Shot two: extreme close up of the sole tread pattern, a hard light sweeps from the left across the rubber surface revealing the groove geometry. Shot three: the shoe descends from above into frame and lands on a matte pale stone plinth, a few fine dust particles lift gently at the instant of contact, generous negative space. Seamless gradient backdrop, hard specular light, shallow depth of field, restrained palette, no text, no logo, no people.",
              "model.aspect_ratio": "16:9",
              "model.quality": "720p",
              "model.duration_seconds": 10,
              "model.generate_audio": true,
              "model.multi_clip": false,
              "model.seed": 2081797219,
              "control_after_generate#1": "randomize",
              "model.negative_prompt": "text, letters, words, typography, watermark, logo, brand mark, UI, screen content, subtitles, caption, people, hands, human, cartoon, illustration, oversaturated colors, lens flare artifacts, chroma noise, watermark border, clutter",
              "control_after_generate": "randomize"
          },
          "color": "#432",
          "bgcolor": "#653"
      },
      {
          "id": 3,
          "type": "SaveVideo",
          "pos": [
              1000,
              40
          ],
          "size": [
              400,
              560
          ],
          "flags": [],
          "order": 2,
          "mode": 0,
          "inputs": [
              {
                  "name": "video",
                  "type": "VIDEO",
                  "link": 1
              }
          ],
          "outputs": [
              {
                  "name": "video",
                  "type": "VIDEO",
                  "links": null
              }
          ],
          "properties": {
              "Node name for S&R": "SaveVideo"
          },
          "widgets_values": [
              "video/PixVerse_v6max_t2v",
              "auto",
              "auto",
              "auto"
          ],
          "widgets_values_named": {
              "filename_prefix": "video/PixVerse_v6max_t2v",
              "format": "auto",
              "format.codec": "auto",
              "codec": "auto"
          }
      }
  ],
  "links": [
      [
          1,
          1,
          0,
          3,
          0,
          "VIDEO"
      ]
  ],
  "groups": [],
  "config": [],
  "extra": {
      "ds": {
          "scale": 0.8435999925401471,
          "offset": [
              384.5779289641189,
              313.9476135772917
          ]
      },
      "frontendVersion": "1.57.1",
      "VHS_latentpreview": false,
      "VHS_latentpreviewrate": 0,
      "VHS_MetadataImage": true,
      "VHS_KeepIntermediate": true
  },
  "version": 0.4
161}
PixVerse V6 Max：文生视频

节点构成

官方标注的模型

工作流 JSON 复制

工作流 JSON
