<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/mX1OIrjj6hk" start="0"></iframe></div>Watch the full video first if you want to understand how this Bernini-R reference video conditioning workflow works in practice. The video shows how a source video and a reference video can be connected into one controlled editing pipeline, where the reference video becomes part of the edited scene while the original video structure remains stable.This ComfyUI workflow is designed for Bernini-R reference video conditional editing. Its main purpose is to take an existing source video and use another video as a visual condition, allowing the workflow to insert, propagate, or integrate the reference video content into the target scene. Compared with simple text-to-video generation, this is a more controlled video editing workflow because it uses both source video structure and reference video content at the same time.The workflow is built around the Bernini-R high-noise and low-noise model route. It uses Bernini_HIGH_fp8_e4m3fn_scaled.safetensors and Bernini_LOW_fp8_e4m3fn_scaled.safetensors as the dual model branches. It also uses UMT5 XXL fp8 text encoding, Wan 2.1 VAE, BerniniConditioning, LoadVideo, GetVideoComponents, KSamplerAdvanced, VAEDecode, CreateVideo, and SaveVideo. The model branches are also patched through PathchSageAttentionKJ, which helps the workflow run the Bernini route with a more optimized attention setup.The key node is BerniniConditioning. In this workflow, BerniniConditioning receives both the source video and the reference video. The source video provides the base scene, motion, camera structure, timing, and audio. The reference video provides the visual content that should be inserted or used as the editing condition. This is different from a simple reference image workflow, because the reference input itself contains temporal motion and video information.The example prompt in this workflow is designed around a reference video appearing as an F1 championship video looping on a billboard in a street scene. This is a very clear use case: the source scene keeps its own environment and camera framing, while the reference video becomes embedded as a dynamic screen, billboard, or video surface inside the scene. This makes the workflow useful for screen replacement, billboard insertion, in-scene video advertising, dynamic poster replacement, and reference-video-driven scene editing.The generation route uses a two-stage KSamplerAdvanced structure. The first sampler handles the high-noise stage, building the main transformation and integrating the reference condition into the target video. The second sampler handles the low-noise stage, refining details and stabilizing the final visual result. The workflow also connects LightX2V-style LoRA branches and UnifiedReward-Flex LoRA branches for both high and low model paths, helping improve efficiency and final output quality.Compared with ordinary video-to-video workflows, this Bernini-R reference video workflow is more specialized for conditional video insertion. A normal V2V workflow may redraw the whole scene or fail to preserve the reference video content clearly. This workflow gives creators a more direct structure for combining a source video with another video reference.This workflow is suitable for billboard video replacement, screen content replacement, advertising insertion, reference video propagation, video-in-video effects, street scene edits, product display videos, cinematic environment editing, Bilibili showcases, YouTube tutorials, RunningHub releases, and Civitai workflow publishing.Main features:<ul><li>Bernini-R reference video conditional editing workflow</li><li>Source video + reference video input</li><li>Reference video can be embedded into the target scene</li><li>Suitable for billboard, screen, and ad insertion tasks</li><li>Bernini HIGH / LOW fp8 dual-model route</li><li>UMT5 XXL fp8 text encoder</li><li>Wan 2.1 VAE decoding</li><li>BerniniConditioning with source video and reference video</li><li>PathchSageAttentionKJ optimization</li><li>Two-stage KSamplerAdvanced generation</li><li>LightX2V high / low noise LoRA support</li><li>UnifiedReward-Flex high / low noise LoRA support</li><li>CreateVideo and SaveVideo final output</li><li>Better suited for conditional V2V than simple text-only editing</li></ul>Suggested workflow:Prepare a clean source video first. The target area should be easy to understand, especially if you want to insert the reference video into a billboard, screen, signboard, wall display, or background object. Then prepare the reference video that you want to place or propagate into the scene. Load both videos into the workflow and write a prompt that clearly explains the relationship between them. For example, describe where the reference video should appear, how it should be framed, whether it should loop, and what parts of the original scene must remain unchanged. Start with a short test clip first. If the reference video does not appear clearly, make the insertion target more explicit. If the source scene changes too much, strengthen preservation rules for camera framing, lighting, motion, background, and original scene structure.⚙️ RunningHub WorkflowTry the workflow online right now — no installation required. 👉 Workflow: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2062503695899783170?inviteCode=rh-v1111">https://www.runninghub.ai/post/2062503695899783170?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/BV1yLEc6dEJc/">https://www.bilibili.com/video/BV1yLEc6dEJc/</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/2062503695899783170?inviteCode=rh-v1111">https://www.runninghub.ai/post/2062503695899783170?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/BV1yLEc6dEJc/">https://www.bilibili.com/video/BV1yLEc6dEJc/</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: 18f63f8d0adfa3558f1feb77a72ffee6995a596396d7fd480ea997328365d66b