Allows you to extend existing videos using keyframes.
Runtime profile
Source description
SVI2Pro+FLFVideoExtension
Allows you to extend existing videos using keyframes.
SVI2PRO FLF V1.1
Added a switch to enable/disable end_samples (Last Frame) directly, without manually connecting/disconnecting inputs. This toggles the First/Last Frame functionality: if disabled, the node reverts to the base SVI 2 PRO behavior. (Requires updating the Wan-SVI2Pro-FLF nodes to the latest version)
Added contrast adjustment widget, useful if your output looks washed out.
SVI2PRO FLF V1
Workflow for ComfyUI that combines SVI 2 Pro motion continuity with Wan 2.2 First/Last Frame (FLF) style control over the end of a clip, enabling smooth video generation from a sequence of frames.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This ComfyUI workflow extends an existing video into a continuation using a video, prompt, and keyframes; its experimental loop mode uses Start, Loop, and End images plus three prompts to create a sequence with a repeating action.
Video extension pairs SVI 2 PRO motion continuity with Wan 2.2 First/Last Frame control over the end of a clip.
Loop mode moves from Start to loop entry, repeats the loop action, then exits to the final frame; the action can vary by cycle when increment is enabled.
For video extension, load an existing video and add a prompt; the described output is a continuation.
Loop mode takes Start, Loop, and End images with three prompts matched to their transitions, producing a sequence that repeats the loop action before reaching the final frame.
To use First/Last Frame control, update the Wan-SVI2Pro-FLF nodes to the latest version.
Listed model files include `rife49.pth`, `wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors`, `RealESRGAN_x4plus.safetensors`, `SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors`, and `wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors`.
Other listed model files are `umt5_xxl_fp8_e4m3fn_scaled.safetensors`, `wan_2.1_vae.safetensors`, `wan22EnhancedNSFWCameraPrompt_nsfwFASTMOVEV2Q8L.gguf`, `wan22EnhancedNSFWCameraPrompt_nsfwFASTMOVEV2Q8H.gguf`, and `SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors`.
Listed node packs include `comfyui-impact-pack`, `comfyui-customnodes-template`, `comfyui_essentials`, `comfyui_layerstyle`, `comfyui-gguf`, and `comfyui-videohelpersuite`. The list also names `comfyui-frame-interpolation`, `rgthree-comfy`, `pr-was-node-suite-comfyui-47064894`, `
Use the `end_samples` switch to turn Last Frame control on or off; when off, the node returns to base SVI 2 PRO behavior.
If an output looks washed out, try the contrast adjustment.
Suggestion · not verified
For loop mode, match each prompt to its corresponding image transition.
Suggestion · not verified
Before downloading, verify that the Civitai page title and version match this video continuation workflow and `3-Stage Loop Automation`; before setup, confirm where to get `comfyui-gguf`, `ComfyMath`, `pr-was-node-suite-comfyui-47064894`, the two named camera prompt files, and `
Suggestion · not verified
The 3-Part Loop Mode is labeled experimental, and no license is listed; check its behavior and usage terms before reuse.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 1780 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
SVI2PRO VideoExtension
This workflow uses SVI 2 PRO to extend existing videos: just load your video, add a prompt, and watch it seamlessly generate the continuation.
3-Stage Loop Automation
Experimental: 3-Part Loop Mode
Uses 3 images (Start / Loop / End) and 3 prompts to automate sequences:
Start → Loop entry
Repeating loop action (varies per cycle if increment is enabled)
Loop exit → Final frame
Ensure prompts match their corresponding image transitions.
If you like these workflows, I’d love to see your results, please share your videos in the Gallery or link them in the comments.
Repository:
Recommended models for these workflows:
SFW:
NSFW:
Estimated VRAM requirement
Estimate unavailable
8.86 GB across 5 of 10 model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
23 requirementsUpscaler · 63.8 MB · SAFETENSORS · Hugging Face · Comfy-Org/Real-ESRGAN_repackaged
Checkpoint · Hugging Face · VMTamashii/rife49
LoRA · Hugging Face
LoRA · Hugging Face · alphaghost13/SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16
Text encoder · 6.27 GB · Hugging Face · Comfy-Org/Wan_2.1_ComfyUI_repackaged
VAE · 242 MB · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
LoRA · 1.14 GB · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
LoRA · 1.14 GB · SAFETENSORS · Hugging Face · Comfy-Org/Wan_2.2_ComfyUI_Repackaged
wan22EnhancedNSFWCameraPrompt_nsfwFASTMOVEV2Q8H.gguf
Not resolvedCheckpoint · Unknown
wan22EnhancedNSFWCameraPrompt_nsfwFASTMOVEV2Q8L.gguf
Not resolvedCheckpoint · Unknown
ComfyMath
PossibleNode pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
comfyui-gguf
PossibleNode pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
pr-was-node-suite-comfyui-47064894
Not resolvedNode pack · Registry
Node pack · Registry