ComfyUI Node
Apply FLOAT Synthesis (VA)
The final image generation step. It takes the bundled appearance latents (from the Appearance Pipe) and the driven motion sequence (r_d), then uses the loaded Synthesis/Decoder model to render the final animated image sequence frame by frame.
Apply FLOAT Synthesis (VA)
- appearance_pipe
- float_synthesis
- r_d_latents
- images
- float_synthesis_out
CategoryFLOAT/Very Advanced
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| appearance_pipe | FLOAT_APPEARANCE_PIPE | The bundled appearance information (s_r latent and feature maps) from the ApplyFloatEncoder node. (Ws→r) | |
| float_synthesis | FLOAT_SYNTHESIS_MODEL | The loaded FLOAT Synthesis (Decoder) model module. | |
| r_d_latents | TORCH_TENSOR | The driven motion latent sequence generated by the FMT sampler. (Wr→D) |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| images | IMAGE | — |
| float_synthesis_out | FLOAT_SYNTHESIS_MODEL | — |