ComfyUI Node
H3 Video Upsampler (file to file)
The upsampler from a video file straight to an MP4. It works a piece at a time, so RAM stays low however long the clip is. Same result as the IMAGE node; frame rate and sound come from the file.
H3 Video Upsampler (file to file)
- video
- model
- vae
- conditioning
- audio_vae
- video
- filepath
- report
◄upscale_model▾►
◄megapixels2.00►
◄denoise0.800►
◄loraopen_h3_regenerate_2k_r256pp_bf16.safetensors►
◄tile_tokens0►
◄sampler_nameeuler►
◄redraw_seed42►
◄attentionsparse►
◄chunk_joinstepped►
◄chunkingtrue►
◄tilingtrue►
◄redraw_start0.60►
◄redraw_steps3 (recipe)►
◄frame_genoff►
◄codecauto►
◄qualitymax►
◄filename_prefixvideo/H3_upsampled►
◄frame_ratesource►
◄reuse_encodedtrue►
CategoryPlagueKind/minimax/upscaler
Inputs (24)
| Name | Type | Default | Description |
|---|---|---|---|
| video | VIDEO | The clip (Load Video or Load Video (path)). It's read a piece at a time, so any length works; frame rate and sound come from the file. | |
| model | MODEL | The H3 model (UNETLoader: minimax_h3_fl2va_pruned_int8_convrot). | |
| vae | VAE | The H3 video VAE. Tip: the sol-VAE (minimax_h3_sol_vae_fp16) made a whole run about 20% faster in tests, with hair edges a touch softer. | |
| upscale_model | COMBO | The 3D latent upscaler, from models/latent_upscale_models (minimax_h3_latent_upscaler_3d_bf16.safetensors). | |
| megapixels | FLOAT | 2.000.1–16 | Output size. 2 = about 1920x1080. The shape of the clip is kept. |
| denoise | FLOAT | 0.8000–1 | How strongly the Regen2K LoRA re-draws detail. 0.8 = normal. 0 = no re-draw, the clip is only enlarged. |
| lora | COMBO | open_h3_regenerate_2k_r256pp_bf16.safetensors | The Regen2K LoRA, from models/loras (open_h3_regenerate_2k_r256pp_bf16.safetensors). |
| tile_tokens | INT | 00–1048576 | How much work goes to the GPU at once. 0 = automatic (recommended): it learns what your card can take and remembers it for the next run. A number fixes it: lower uses less VRAM, by cutting the clip into shorter pieces and then tiles. |
| sampler_name | COMBO | euler | Keep euler: Regen2K is tuned for it. |
| redraw_seed | INT | 420–2147483647 | Noise seed for the re-draw. Same seed, same result. |
| attention | COMBO | sparse | sparse (default) = ComfyUI's sparse attention: in side-by-side tests a whole run was 28% faster and looked the same. dense = exact attention, slower. A ComfyUI without sparse attention runs dense. |
| chunk_join | COMBO | stepped | How the overlapping pieces of a long clip are joined. stepped (recommended) = all pieces are re-drawn together and agree at every step, so faces don't change at a join. crossfade = each piece is re-drawn on its own and the overlaps are blended (the old way; a face can shift at a join). Same speed. |
| chunking | BOOLEAN | true | On = a long clip may be cut into overlapping pieces (about 4 s each) when it's too much for the GPU at once. Off = the whole clip in one go: no joins, but VRAM grows with length, so very long clips are cut anyway. |
| tiling | BOOLEAN | true | On = when even a short piece is too much for the GPU, each frame may also be cut into overlapping tiles. Off = never tile; if VRAM runs out, it stops with a message saying what to change. |
| redraw_start | FLOAT | 0.600.3–0.95 | How much the re-draw is allowed to change. 0.6 (default) keeps faces close to your clip. 0.8 = the original Regen2K recipe: sharper, but faces drift more. Lower than 0.6 changes less again and sharpens less. |
| redraw_steps | COMBO | 3 (recipe) | Re-draw steps. 3 = the Regen2K recipe. 2 = a third faster; in side-by-side tests it looked the same. |
| frame_gen | COMBO | off | Doubles the frame rate while saving (24 -> 48 fps) with RTX frame generation. Needs an RTX card and nvidia-vfx. |
| codec | COMBO | auto | auto = the GPU encoder when there is one, otherwise the CPU. |
| quality | COMBO | max | File quality. Lower = smaller file. |
| filename_prefix | STRING | video/H3_upsampled | Start of the file name in ComfyUI's output folder. A folder works too: video/mine. |
| frame_rate | COMBO | source | source = keep every frame. 24 = convert to H3's own 24 fps while reading: lip sync is exact and a 48 fps clip is half the work. Use frame_gen x2 to get 48 fps back. |
| reuse_encoded | BOOLEAN | true | Remember the prepared clip (about 100 MB a minute, in ComfyUI's temp folder), so re-running the same clip with other settings starts faster. Cleared when ComfyUI restarts. |
| conditioningopt | CONDITIONING | Optional: a text prompt (CLIPTextEncode with the H3 text encoder) describing the clip. Describe the look ("2D anime, flat cel shading, clean line art") more than the objects. Unwired = no prompt, which works well for most clips. | |
| audio_vaeopt | VAE | The H3 audio VAE. Lets the re-draw hear the soundtrack, which keeps mouths in sync. Without it the re-draw hears silence. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| filepath | STRING | — |
| report | STRING | — |