Updated: Jun 6, 2026
character
Watch the full video first if you want to understand how this Bernini-R single-image reference video workflow works in practice. The video shows how one reference image can be expanded into a finished cinematic video, how the prompt enhancement chain converts a rough idea into a stronger Bernini instruction, and how to run the full workflow online without rebuilding a local ComfyUI environment.
This ComfyUI workflow is designed for Bernini-R single-image reference video generation. Its main purpose is to take one reference image, or an expandable batch of reference images, and generate a complete video clip from it. Unlike a pure text-to-video workflow, this graph uses the reference image as the visual anchor, so the final video can preserve subject identity, style direction, visual mood, and composition logic more effectively.
The workflow is built around the Bernini-R high-noise and low-noise model structure. 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, KSamplerAdvanced, PathchSageAttentionKJ, VAEDecode, CreateVideo, and SaveVideo. The model chain also includes LightX2V-style LoRA support and UnifiedReward-Flex LoRA support for both high-noise and low-noise routes, helping the final result stay more efficient, coherent, and visually polished.
The reference image side is flexible. The workflow includes multiple LoadImage nodes, image scaling nodes, and BatchImagesNode. This means the graph can be used as a single-image reference workflow, but it can also expand into multi-reference input when needed. The image is scaled and prepared before entering BerniniConditioning, where it becomes the visual condition for the generated video.
The prompt side is one of the strongest parts of this workflow. BerniniPromptEnhancer is used to build a Bernini-specific prompt structure. In the uploaded graph, the task type is set around r2v / reference-to-video logic, and the example prompt describes an epic cinematic fantasy scene in a collapsing floating holy city above the clouds. The prompt is then passed into RHLLMChatNode, which rewrites the instruction into a more complete video-generation prompt. After that, StringReplace nodes clean the JSON wrapper, and the final rewritten text is automatically connected into the positive prompt encoder.
The generation path uses BerniniConditioning with a vertical video setup. The workflow is configured around 480×848 and 129 frames, making it suitable for short vertical videos, social media clips, fantasy scenes, character shots, and cinematic concept previews. The KSamplerAdvanced structure uses a two-stage process: a high-noise stage for main motion and scene construction, and a low-noise stage for refinement and final stabilization.
Compared with ordinary image-to-video workflows, this Bernini-R workflow is more specialized for reference-based cinematic generation. A normal I2V workflow may simply animate an image, but this graph combines reference image conditioning, LLM prompt expansion, Bernini task prompting, dual-model sampling, SageAttention optimization, and final video output into one more production-ready route.
Main features:
Bernini-R single-image reference video workflow
Supports expandable multi-reference image batching
Reference-to-video / image-to-video generation logic
Bernini HIGH / LOW fp8 dual-model route
UMT5 XXL fp8 text encoder
Wan 2.1 VAE decoding
BerniniPromptEnhancer prompt creation
RHLLMChatNode automatic prompt rewriting
JSON cleanup chain for LLM output
BerniniConditioning i2v / r2v control
PathchSageAttentionKJ optimization
LightX2V high / low noise LoRA support
UnifiedReward-Flex high / low noise LoRA support
KSamplerAdvanced two-stage generation
CreateVideo and SaveVideo final output
Suggested workflow:
Prepare one strong reference image first. The subject should be clear, the composition should be readable, and the style direction should already match the kind of video you want to create. Load the image into the workflow and write a direct scene prompt describing the subject, environment, motion, camera movement, lighting, atmosphere, and story direction. Let BerniniPromptEnhancer and RHLLMChatNode rewrite the prompt into a more complete Bernini instruction. Check the cleaned prompt before rendering. If the video does not follow the reference strongly enough, simplify the prompt and make the preservation rules clearer. If the result lacks motion, describe the camera move, subject action, environmental motion, and scene progression more explicitly. Start with the default vertical setup first, then adjust resolution, length, and reference images after the base result is stable.
⚙️ RunningHub Workflow
Try the workflow online right now — no installation required.
👉 Workflow: https://www.runninghub.ai/post/2062503688601690114?inviteCode=rh-v1111
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 & 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: https://www.bilibili.com/video/BV1yLEc6dEJc/
☕ Support Me on Ko-fi
If 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: https://ko-fi.com/aiksk
💼 Business Contact
For 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： https://www.runninghub.ai/post/2062503688601690114?inviteCode=rh-v1111
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： https://www.bilibili.com/video/BV1yLEc6dEJc/
我会在 夸克网盘 持续更新模型资源：
👉 https://pan.quark.cn/s/20c6f6f8d87b
这些资源主要面向本地用户，方便进行创作与学习。