EasyUse/Loadersgenerated
EasyLoader (Mochi)(mochiLoader)
Loads a Mochi checkpoint and VAE, encodes the provided positive and negative prompts, creates an empty latent with the requested dimensions, length, and batch s...
mochi Loader
model_override
clip_override
vae_override
pipe
model
vae
ckpt_name
COMBO
vae_name
mochi_vae.safetensors
positive
STRING
negative
STRING
resolution
width x height (custom)
empty_latent_width
INT
empty_latent_height
INT
length
INT
batch_size
1
Easy Use
Description
Loads a Mochi checkpoint and VAE, encodes the provided positive and negative prompts, creates an empty latent with the requested dimensions, length, and batch size, and returns an EasyUse pipeline along with the loaded model and VAE. It is intended for Mochi video generation workflows and is located in the EasyUse/Loaders category.
Inputs
| Name | Type | Default | Description |
|---|---|---|---|
ckpt_name | COMBO | none | Mochi checkpoint file to load. |
vae_name | COMBO | mochi_vae.safetensors | VAE file to load with the checkpoint. |
positive | STRING | "" | Positive prompt used to guide generation. |
negative | STRING | "" | Negative prompt used for CFG; leave empty for unconditional guidance. |
resolution | COMBO | width x height (custom) | Selection of preset output resolutions. Leave on width x height (custom) to use the manual empty_latent_width and empty_latent_height values. |
empty_latent_width | INT | none | Width of the generated latent / output frames. |
empty_latent_height | INT | none | Height of the generated latent / output frames. |
length | INT | none | Number of frames to generate for the Mochi video. |
batch_size | INT | 1 | Number of video samples to generate in parallel. Min 1, max 4096. |
model_override | MODEL | optional | Supply a model to use instead of loading one from ckpt_name. |
clip_override | CLIP | optional | Supply a CLIP text encoder to use instead of the checkpoint’s CLIP. |
vae_override | VAE | optional | Supply a VAE to use instead of vae_name. |
Outputs
| Type | Description |
|---|---|
PIPE_LINE | EasyUse pipeline containing the loaded model, VAE, conditioning, empty latent, and generation settings for downstream EasyUse nodes. |
MODEL | Loaded Mochi diffusion model. |
VAE | Loaded Mochi VAE, useful for decoding latents to video. |
Usage Notes
- This node is designed for Mochi video generation: set
lengthto the desired number of frames, then use theMODELoutput with standard sampling nodes for video. positiveandnegativeare text strings. They are encoded internally, so this node does not expose a separate CLIP output.- When
resolutionis left onwidth x height (custom), the manualempty_latent_widthandempty_latent_heightfields control the spatial dimensions. - The
PIPE_LINEoutput is the most convenient connection point for other EasyUse nodes; theMODELandVAEoutputs are available when you need to wire standard ComfyUI nodes directly. - Memory usage scales with
batch_size,length, and the chosen width and height, so increase these values conservatively. - Use the optional override inputs when you already have a loaded model, CLIP, or VAE in your workflow and want to avoid reloading files.
Comments
Sign in with GitHub to join the discussion.