Kling 3.0 Models Are Now Available in ComfyUI!
Multi-shot in one generation, new consistency level, multilingual dialogue and 15s generation.
- Use Case
- Video
- Best For
- Video
- Reading Time
- 2 min
Workflow Overview
Multi-shot in one generation, new consistency level, multilingual dialogue and 15s generation.
Content type: Workflow
Primary intent: Download
Setup Notes
- Install the required models before opening the workflow template.
- Use the download button above to import the workflow JSON into ComfyUI.
Key Announcement: Kling 3.0 Models Now Integrated with ComfyUI
Cutting-edge multi-modal capabilities arrive in ComfyUI through Partner Nodes, enabling developers early access to one of the most sophisticated generative frameworks.
Enhanced Functionality Includes:
Kling Video 3.0
Kling Video 3.0 Omni
Kling Image 3.0
Kling Image 3.0 Omni
Seamlessly incorporate Kling’s latest visual, auditory, and storytelling features into your node-based workflows.
1. Single-Generation Multi-Shot Duration Management
The upgraded Multi-Shot feature interprets scene requirements directly from your input, auto-designing:
Camera perspectives
Composition frameworks
Dialogue sequencing
Voice-over integration
Artists can now specify the desired shot count per session and assign precise timing per segment, eliminating manual editing needs.
Input Example:
Section 1: Rapid motion following a motorbike mid-wheelie alongside a galloping horse, light dust rising
Section 2: Ground-level focus on equine hooves and bicycle wheel
Section 3: Rear-angle perspective of the rider on the motorcycle
Section 4: Ultra-slow capture of the horse mid-leap

Download Kling v3 I2V Workflow File
2. Subject Stability in Image-to-Video Conversion
Kling 3.0 advances reference-guided creation:
Accommodates multi-image/video inputs as contextual elements
Establishes consistent identities for objects, environments, and personas
Ensures uniformity across motion and scene progression
Enables professional-grade continuity for narrative sequences and brand integrations in ComfyUI.
3. Integrated Multilingual Audio Recognition
Audio synthesis now aligns with situational context:
Targeted control over speaker assignment in group interactions
Covers Chinese, English, Japanese, Korean, Spanish
Authentic dialect fidelity and linguistic blending
Realistic facial syncing during speech
4. Fluid On-Screen Text Integration
Kling 3.0 delivers reliable structured textual rendering:
Maintains source markings and subtitles
Creates novel layout-responsive typography
Enhances realism for promotional, interface, and branded sequences
A critical advancement toward deployable commercial media generation.
Launch Guide for ComfyUI
Update ComfyUI to its newest version or reach the online platform
Within Template Library, search for
Kling 3.0 VideoframeworksCapture actionable insights:

Acquire the fitting model sequence and initialize execution!
Kling V3 Omni Video Edit Workflow
Happy innovating!