ComfyUI Node
WanVideo Looper
A ComfyUI node in WanVideoLooper with 27 inputs and 2 outputs.
WanVideo Looper
- model_high
- model_low
- clip
- vae
- start_image
- positive_prompts
- clip_vision
- model_clip_sequence
- color_match_ref
- images
- last_frame
◄negative_prompt—►
◄seed0►
◄steps6►
◄cfg_motion_noise1.0►
◄cfg_noise1.0►
◄sampler_name▾►
◄scheduler▾►
◄model_switch_point0.900►
◄sigma_shift8.00►
◄denoise1.00►
◄width832►
◄height480►
◄frame_merge1►
◄duration_sec5►
◄color_match_methodDisabled►
◄color_match_reference_frameFirst Frame►
◄color_match_strength1.00►
◄enable_dry_runfalse►
CategoryWanVideoLooper
Inputs (27)
| Name | Type | Default | Description |
|---|---|---|---|
| model_high | MODEL | The BASE high-noise model (can be pre-patched with global LoRAs). | |
| model_low | MODEL | The BASE low-noise model (can be pre-patched with global LoRAs). | |
| clip | CLIP | The BASE CLIP model (can be pre-patched with global LoRAs). | |
| vae | VAE | The VAE model used for decoding the final image. | |
| start_image | IMAGE | The seed image that the first loop will start from. | |
| positive_prompts | * | Connect the 'prompt_list' output from the WanVideo Multi-Prompt node. | |
| negative_prompt | STRING | A single, global negative prompt applied to all loops. | |
| seed | INT | 00–18446744073709550000 | The random seed. This will be used for all loops. |
| steps | INT | 61–10000 | The total number of sampling steps for each loop. |
| cfg_motion_noise | FLOAT | 1.00–100 | CFG for the first step ONLY. A value > 1.0 will engage the negative prompt for initial motion guidance. Set to 1.0 to disable motion guidance. |
| cfg_noise | FLOAT | 1.00–100 | Classifier-Free Guidance scale for both high and low noise models. 1.0 disables guidance. |
| sampler_name | COMBO | The sampling algorithm (e.g., dpmpp_2m_sde_gpu). | |
| scheduler | COMBO | The noise scheduler (e.g., karras). | |
| model_switch_point | FLOAT | 0.9000–1 | Timestep to switch from high-noise to low-noise model. 0.9 (I2V) or 0.875 (T2V) recommended. |
| sigma_shift | FLOAT | 8.000–100 | Applies sigma shift to both models. 8.0 is a good default. |
| denoise | FLOAT | 1.000–1 | Denoise amount. 1.0 means generate a full new image. |
| width | INT | 83264–8192 | The width of the output video. |
| height | INT | 48064–8192 | The height of the output video. |
| frame_merge | INT | 10–8 | Number of frames to overlap/merge between loops for smooth transitions. |
| duration_sec | INT | 51–10 | Duration of each segment in seconds. 5s is recommended, max 10. |
| color_match_method | COMBO | Disabled | 'Disabled': No color matching is applied. 'Reinhard (GPU)': Applies Reinhard color transfer. 'MKL (GPU)': Applies MKL color transfer. |
| color_match_reference_frame | COMBO | First Frame | 'First Frame': Matches all frames to the very first frame of the entire sequence. 'Last Frame': Matches all frames to the very last frame of the entire sequence. 'Sequential': Matches each segment to the last frame of the previous segment. 'Reference': Matches all frames to the optional 'color_match_ref' image. |
| color_match_strength | FLOAT | 1.000–1 | Strength of the internal color matching (1.0 = full match). |
| enable_dry_run | BOOLEAN | false | If enabled, skips sampling and decoding to quickly check setup and logs. |
| clip_visionopt | CLIP_VISION | (Optional) A CLIP Vision model for guiding the start image. | |
| model_clip_sequenceopt | ANY | (Optional) Connect a WanVideo Lora Sequencer to use different pre-patched models/clips per segment. | |
| color_match_refopt | IMAGE | (Optional) Static reference image for internal color matching. If omitted, uses last frame of previous segment. |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| last_frame | IMAGE | — |