ComfyUI Node
Smart Mobius WAN Loop
Mobius seamless loop for WAN 2.2 dual-pass (high/low noise). Three independent mechanisms: (1) Latent shift — cycles frame positions across denoising steps to distribute RoPE bias. (2) Loop blend — corrects end-frame noise by blending toward start-frame predictions. (3) Circular RoPE — compresses temporal positions so the last frame is closer to the first in attention space.
Smart Mobius WAN Loop
- model_high
- model_low
- positive
- negative
- vae
- start_image
- end_image
- clip_vision_start_image
- clip_vision_end_image
- model_high
- model_low
- positive
- negative
- latent
◄width832►
◄height480►
◄length81►
◄batch_size1►
◄motion_amplitude1.00►
◄enable_latent_shifttrue►
◄shift_skip0►
◄enable_loop_blendtrue►
◄blend_frames5►
◄blend_strength0.50►
◄enable_circular_ropetrue►
◄roll_concat_conditioningfalse►
◄circular_rope_strength0.50►
CategorySmartHelperNodes/Wan
Inputs (22)
| Name | Type | Default | Description |
|---|---|---|---|
| model_high | MODEL | — | |
| model_low | MODEL | — | |
| positive | CONDITIONING | — | |
| negative | CONDITIONING | — | |
| vae | VAE | — | |
| width | INT | 83216–8192 | — |
| height | INT | 48016–8192 | — |
| length | INT | 811–8192 | — |
| batch_size | INT | 11–4096 | — |
| start_imageopt | IMAGE | — | |
| end_imageopt | IMAGE | — | |
| clip_vision_start_imageopt | CLIP_VISION_OUTPUT | — | |
| clip_vision_end_imageopt | CLIP_VISION_OUTPUT | — | |
| motion_amplitudeopt | FLOAT | 1.001–2 | 1.0 = official FLF, 2.0 = max structural repulsion boost |
| enable_latent_shiftopt | BOOLEAN | true | Mobius-style circular latent rolling each denoising step |
| shift_skipopt | INT | 00–100 | Roll stride per step. 0 = auto (coprime with latent frame count) |
| enable_loop_blendopt | BOOLEAN | true | Blend end-frame predictions toward start-frame predictions after CFG |
| blend_framesopt | INT | 51–20 | Number of end frames to correct via boundary blending |
| blend_strengthopt | FLOAT | 0.500–1 | 0 = no correction, 1 = fully replace end with start predictions |
| enable_circular_ropeopt | BOOLEAN | true | Compress temporal RoPE so last frame is closer to first |
| roll_concat_conditioningopt | BOOLEAN | false | Experimental. Roll concat_mask/concat_latent_image together with the latent cycle. |
| circular_rope_strengthopt | FLOAT | 0.500–1 | 0 = no change, 1 = maximum temporal compression |
Outputs (5)
| Name | Type | Description |
|---|---|---|
| model_high | MODEL | — |
| model_low | MODEL | — |
| positive | CONDITIONING | — |
| negative | CONDITIONING | — |
| latent | LATENT | — |