ComfyUI Node
Wan Chunked I2V Sampler ♾️
All-in-one chunked video generator for Wan I2V models. Set total_frames and chunk_frames — the node handles everything: encode → sample → decode → extract reference → repeat. Supports single-pass (one model) or two-pass (connect model_b). FLF (First-Last-Frame): Connect an end_image to make the video transition toward a target end frame. For multi-chunk videos, set end_blend_chunks (e.g. 9–17) for a smooth crossfade overlap. Uses the proven concat approach: each chunk's first frame naturally matches the previous chunk's last frame, so we just drop it and concatenate. Requires: ComfyUI-WanVideoWrapper
Wan Chunked I2V Sampler ♾️
- model
- vae
- start_image
- model_b
- text_embeds
- text_embed_sequence
- clip_embeds
- feta_args
- context_options
- end_image
- video
- total_frames
- chunks_generated
◄total_frames161►
◄chunk_frames81►
◄width832►
◄height480►
◄keep_proportioncrop►
◄crop_positioncenter►
◄steps8►
◄cfg2.00►
◄shift11.00►
◄seed0►
◄force_offloadtrue►
◄schedulereuler►
◄enable_vae_tilingfalse►
◄split_step4►
◄cfg_b1.00►
◄noise_aug_strength0.00►
◄start_latent_strength1.00►
◄end_latent_strength1.00►
◄riflex_freq_index0►
◄tile_x272►
◄tile_y272►
◄tile_stride_x144►
◄tile_stride_y128►
◄end_blend_chunks0►
CategoryVideoChunkTools
Inputs (34)
| Name | Type | Default | Description |
|---|---|---|---|
| model | WANVIDEOMODEL | Wan I2V model (2.1 or 2.2). Runs all steps in single-pass. In two-pass mode, runs the first steps (0 → split_step). | |
| vae | WANVAE | Wan VAE model | |
| start_image | IMAGE | Reference image for the first chunk | |
| total_frames | INT | 1615–9999 | Total frames to generate. Output may be slightly more (rounded to fill the last chunk), then trimmed. |
| chunk_frames | INT | 815–241 | Frames per chunk. Auto-normalized to Wan's 4n+1 rule (5, 9, 13, … 77, 81, 85 …). |
| width | INT | 832128–2048 | Output video width in pixels. |
| height | INT | 480128–2048 | Output video height in pixels. |
| keep_proportion | COMBO | crop | How to resize the input images to match the target width/height. |
| crop_position | COMBO | center | Where to crop or pad the image. |
| steps | INT | 81–100 | Total denoising steps. |
| cfg | FLOAT | 2.000–30 | CFG guidance scale. In two-pass mode this applies to the first pass only. |
| shift | FLOAT | 11.000–1000 | Scheduler shift parameter. |
| seed | INT | 00–18446744073709550000 | Random seed. Same seed used for every chunk — variation comes from different reference images. |
| force_offload | BOOLEAN | true | Offload model to CPU after each sampling pass. Highly recommended. |
| scheduler | COMBO | euler | Noise scheduler algorithm. |
| enable_vae_tiling | BOOLEAN | false | Enable VAE tiling for lower-VRAM decode. May introduce tile seam artifacts. |
| model_bopt | WANVIDEOMODEL | Optional second model for two-pass sampling. Connect this to split denoising across two models (e.g. different LoRA weights). Leave disconnected for single-pass. | |
| split_stepopt | INT | 41–99 | Two-pass only: model runs steps 0 → split_step, model_b runs split_step → end. Ignored in single-pass. |
| cfg_bopt | FLOAT | 1.000–30 | Two-pass only: CFG for the second pass (model_b). Ignored in single-pass. |
| text_embedsopt | WANVIDEOTEXTEMBEDS | Text conditioning from WanVideoTextEncode. Applied to ALL chunks uniformly. | |
| text_embed_sequenceopt | TEXT_EMBED_SEQUENCE | Per-chunk text conditioning from ChainTextEmbeds. Chunk 1 gets embed_1, chunk 2 gets embed_2, etc. Last embed repeats for extra chunks. Overrides text_embeds when connected. | |
| clip_embedsopt | WANVIDIMAGE_CLIPEMBEDS | Optional CLIP vision embeddings from WanVideoClipVisionEncode. | |
| feta_argsopt | FETAARGS | FETA arguments. Recommended: weight=2, start=0, end=1. | |
| context_optionsopt | WANVIDCONTEXT | Context windowing options. In two-pass mode only applied to the first pass (model). | |
| noise_aug_strengthopt | FLOAT | 0.000–1 | Noise augmentation for I2V encoding. 0 = no augmentation. |
| start_latent_strengthopt | FLOAT | 1.000–1 | Strength of the start image in latent space. |
| end_latent_strengthopt | FLOAT | 1.000–1 | FLF only: Strength of the end image conditioning in latent space. Controls how strongly the last chunk is pulled toward the end image. Only effective when end_image is connected. |
| riflex_freq_indexopt | INT | 00–1000 | RIFLEX frequency index. 0 = disabled. |
| tile_xopt | INT | 27240–4096 | VAE decode tile width (only when tiling enabled). |
| tile_yopt | INT | 27240–4096 | VAE decode tile height (only when tiling enabled). |
| tile_stride_xopt | INT | 14432–2040 | VAE decode tile stride X (only when tiling enabled). |
| tile_stride_yopt | INT | 12832–2040 | VAE decode tile stride Y (only when tiling enabled). |
| end_imageopt | IMAGE | Optional target image for the last frame — enables FLF (First-Last-Frame) mode. If a batch of images is provided, they will be distributed as target keyframes across the chunks (e.g., 3 images for a 3-chunk video). | |
| end_blend_chunksopt | INT | 00–40 | FLF only: Number of FRAMES to crossfade at the FLF boundary. The last chunk (with end_image) overlaps with the previous chunk by this many frames, and a smooth alpha ramp blends between them. 0 = hard cut (no crossfade). Try 9–17 for smooth transitions (~0.5–1 sec at 16fps). The last chunk is automatically enlarged to the next valid 4n+1 size to accommodate the overlap. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| video | IMAGE | — |
| total_frames | INT | — |
| chunks_generated | INT | — |