<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/LYXVVBvu8P0" start="0"></iframe></div>Watch the full video first if you want to understand how this EverAnimate long-video consistency editing workflow works in practice. The video shows how an existing video can be edited with reference guidance, pose control, background preservation, character masking, and long-form continuation while keeping the edited result more stable across multiple segments.This ComfyUI workflow is designed for EverAnimate long-video consistency editing. Its main purpose is not only to generate an animated character, but to edit an existing video while preserving the important motion, body structure, background relationship, and temporal continuity. Compared with a simple one-shot video edit, this workflow is built for longer clips where character identity, pose rhythm, mask boundaries, and visual consistency often break after the first segment.The workflow starts from a driving video. VHS video loading and VHS_VideoInfo read the selected FPS, frame count, width, height, and duration. This gives the workflow a stable timeline before generation begins. The source frames are then processed through multiple pose and detection routes, including ViTPose, YOLO, SDPose, PoseAndFaceDetection, DrawViTPose, BBoxYOLO, and SDPoseKeypointExtractor. These preprocessing stages turn the original video into usable pose guidance, body structure information, and motion control signals.The editing part is where this workflow differs from the pure generation version. It includes a character mask path, mask expansion, and block-style mask processing. GrowMaskWithBlur expands and softens the mask, while BlockifyMask converts it into a more usable character-editing mask. This mask is then sent into ComfyEverAnimate as character_mask, together with background_video and pose_video. This allows the workflow to focus the edit on the character area while keeping the background or surrounding structure more stable.The core generation node is ComfyEverAnimate. In the first local editing segment, it receives the reference image, pose video, background video, character mask, positive and negative conditioning, width, height, length, pose strength, face strength, and motion handoff settings. After the first segment is generated, TrimVideoLatent and ComfyEverAnimateTrimImages remove redundant anchor latent frames and duplicate image frames. The workflow then uses continue_motion to pass motion information into the next segment.The long-video logic is handled through a ForLoop structure. The first segment establishes the edited character, mask relationship, motion, and background integration. The continuation segment then receives the previous motion context and keeps generating forward. Each segment is sampled, decoded, trimmed, and batched back into the full sequence. This segmented continuation design is the key reason the workflow is more suitable for long video editing than a standard image-to-video or video-to-video graph.The model route includes Wan-related components, Wan 2.1 VAE, ModelSamplingSD3, CLIPTextEncode for positive and negative prompts, SageAttention acceleration, Torch setting patches, and low-step LCM-style KSampler settings. The negative prompt is designed to suppress overexposure, static frames, blurry details, subtitles, low quality, bad hands, bad faces, deformed limbs, messy backgrounds, extra legs, nudity, and NSFW artifacts.This workflow is suitable for AI dance video editing, character replacement with background preservation, long-form character consistency tests, outfit or subject editing, masked video transformation, digital human motion edits, Bilibili showcases, YouTube tutorials, RunningHub releases, and Civitai workflow publishing.Main features:<ul><li>EverAnimate long-video consistency editing workflow</li><li>Existing video editing with reference guidance</li><li>Pose video and background video control</li><li>Character mask editing structure</li><li>GrowMaskWithBlur mask expansion</li><li>BlockifyMask character mask processing</li><li>ViTPose / YOLO / SDPose preprocessing</li><li>PoseAndFaceDetection body and face analysis</li><li>ComfyEverAnimate local first-segment editing</li><li>continue_motion handoff for continuation segments</li><li>ForLoop structure for longer video editing</li><li>TrimVideoLatent anchor latent trimming</li><li>Duplicate image frame trimming</li><li>Wan 2.1 VAE decoding</li><li>SageAttention acceleration support</li><li>Negative prompt for stability and anti-artifacts</li></ul>Suggested workflow:Prepare a clean source video first. The subject should be visible, the movement should be readable, and the background should not be too chaotic. Then prepare the reference image or edited character direction. Load the video, check FPS, selected frame count, width, and height, then run the pose and mask preprocessing sections. Confirm that pose_video, background_video, and character_mask are usable before entering EverAnimate editing. Start with a short segment first. If the mask edge looks unstable, adjust mask expansion and block processing. If the character changes too much, strengthen the reference and simplify the prompt. If the motion breaks between segments, reduce aggressive motion wording and rely on continue_motion for smoother handoff.⚙️ RunningHub WorkflowTry the workflow online right now — no installation required. 👉 Workflow: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2063900132327907330?inviteCode=rh-v1111">https://www.runninghub.ai/post/2063900132327907330?inviteCode=rh-v1111</a>If the results meet your expectations, you can later deploy it locally for customization.🎁 Fan Benefits: Register to get 1000 points + daily login 100 points — enjoy 4090 performance and 48 GB super power!📺 Bilibili Updates (Mainland China &amp; Asia-Pacific)If you’re in the Asia-Pacific region, you can watch the video below to see the workflow demonstration and creative breakdown. 📺 Bilibili Video: <a target="_blank" rel="ugc" href="https://www.bilibili.com/video/BV1oyET6cEqb/">https://www.bilibili.com/video/BV1oyET6cEqb/</a>☕ Support Me on Ko-fiIf you find my content helpful and want to support future creations, you can buy me a coffee ☕. Every bit of support helps me keep creating — just like a spark that can ignite a blazing flame. 👉 Ko-fi: <a target="_blank" rel="ugc" href="https://ko-fi.com/aiksk">https://ko-fi.com/aiksk</a>💼 Business ContactFor collaboration or inquiries, please contact aiksk95 on WeChat.⚙️打开下方链接即可在线体验，无需安装。 👉 工作流： <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2063900132327907330?inviteCode=rh-v1111">https://www.runninghub.ai/post/2063900132327907330?inviteCode=rh-v1111</a> 如果觉得效果理想，你也可以在本地进行自定义部署。🎁 粉丝福利： 注册即送 1000 积分，每日登录 100 积分，畅玩 4090 体验 48 G 超级性能！📺 Bilibili 更新（中国大陆及南亚太地区）如果你在中国大陆或南亚太地区，可以通过下方视频查看该工作流的实测效果与构思讲解。 📺 B站视频： <a target="_blank" rel="ugc" href="https://www.bilibili.com/video/BV1oyET6cEqb/">https://www.bilibili.com/video/BV1oyET6cEqb/</a>我会在 夸克网盘 持续更新模型资源： 👉 <a target="_blank" rel="ugc" href="https://pan.quark.cn/s/20c6f6f8d87b">https://pan.quark.cn/s/20c6f6f8d87b</a> 这些资源主要面向本地用户，方便进行创作与学习。

Files with SHA256: 10371dbca2ca44dbd2daa78cf57b2af256f41144adb4c3775e0c85c62cde3e52