EasyUse/Loadersgenerated
EasyLoader (Flux)(fluxLoader)
The EasyLoader (Flux) node, class fluxLoader, loads a Flux checkpoint for inference, assembling the model, VAE, LoRA adjustments, prompt, and latent dimensions...
flux Loader
model_override
clip_override
vae_override
optional_lora_stack
optional_controlnet_stack
pipe
model
vae
ckpt_name
COMBO
vae_name
COMBO
lora_name
COMBO
lora_model_strength
1.00
lora_clip_strength
1.00
resolution
1024 x 1024
empty_latent_width
INT
empty_latent_height
INT
positive
STRING
batch_size
1
Easy Use
Description
The EasyLoader (Flux) node, class fluxLoader, loads a Flux checkpoint for inference, assembling the model, VAE, LoRA adjustments, prompt, and latent dimensions into a pipeline. It also supports optional model/CLIP/VAE overrides, a LoRA stack, and a ControlNet stack, making it a flexible single-node loader for Flux workflows.
Inputs
Required
| Name | Type | Default | Notes |
|---|---|---|---|
ckpt_name | COMBO | — | Checkpoint to load. |
vae_name | COMBO | — | VAE to load. |
lora_name | COMBO | — | LoRA to apply to the loaded model. |
lora_model_strength | FLOAT | 1 | Strength of the LoRA on the model weights. Range: -10 to 10, step 0.01. Negative values invert or reduce the effect. |
lora_clip_strength | FLOAT | 1 | Strength of the LoRA on the CLIP weights. Range: -10 to 10, step 0.01. Negative values invert or reduce the effect. |
resolution | COMBO | 1024 x 1024 | Preset resolution for the empty latent. Selecting a preset updates empty_latent_width and empty_latent_height. |
empty_latent_width | INT | — | Width of the empty latent in pixels. |
empty_latent_height | INT | — | Height of the empty latent in pixels. |
positive | STRING | "" | Positive prompt text. |
batch_size | INT | 1 | Number of latents to generate in the batch. Range: 1 to 64. |
Optional
| Name | Type | Notes |
|---|---|---|
model_override | MODEL | Use an existing model instead of loading from ckpt_name. |
clip_override | CLIP | Use an existing CLIP instead of loading from ckpt_name. |
vae_override | VAE | Use an existing VAE instead of loading from vae_name. |
optional_lora_stack | LORA_STACK | Apply multiple LoRAs as a stack. |
optional_controlnet_stack | CONTROL_NET_STACK | Apply multiple ControlNets as a stack. |
Outputs
| Type | Description |
|---|---|
PIPE_LINE | The assembled pipeline containing the model, VAE, conditioning, and latent settings. |
MODEL | The loaded or overridden model. |
VAE | The loaded or overridden VAE. |
Usage Notes
- When
model_override,clip_override, orvae_overrideare provided, they take precedence over the checkpoint and VAE selections. - Use the
resolutionpresets for common Flux dimensions, or setempty_latent_widthandempty_latent_heightdirectly for custom sizes. - The LoRA strength inputs allow negative values, which can be used to weaken or invert a LoRA's influence.
optional_lora_stackandoptional_controlnet_stacklet you compose multiple adapters in a single load.- The
PIPE_LINEoutput can be passed directly to supported sampler or conditioning nodes for further workflow processing.
Comments
Sign in with GitHub to join the discussion.