ComfyUI Node
Apply FLOAT Encoder (VA)
Applies the loaded FLOAT Encoder to a batch of reference images. It preprocesses the images and passes them through the encoder to extract the core appearance latent and multi-scale feature maps, which are bundled into a single Appearance Pipe.
Apply FLOAT Encoder (VA)
- ref_image
- float_encoder
- appearance_pipe (Ws→r)
- r_s_lambda_latent
- float_encoder_out
CategoryFLOAT/Very Advanced
Inputs (2)
| Name | Type | Default | Description |
|---|---|---|---|
| ref_image | IMAGE | A batch of reference images, correctly sized (e.g., 512x512) for the encoder. | |
| float_encoder | FLOAT_ENCODER_MODEL | The loaded FLOAT Encoder model module. |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| appearance_pipe (Ws→r) | FLOAT_APPEARANCE_PIPE | — |
| r_s_lambda_latent | TORCH_TENSOR | — |
| float_encoder_out | FLOAT_ENCODER_MODEL | — |