Model
Trends
.ai
Model
Trends
.ai
the best open source ai models

Load Diffusion Model node in ComfyUI

Load Diffusion Model (UNETLoader) loads a bare denoising network such as Flux, SD3.5, Wan or HunyuanVideo from models/diffusion_models, with a weight_dtype option for fp8 to save VRAM.
Node pack: ComfyUI core
Category: Loaders

What Load Diffusion Model does

Newer model families are not shipped as one all-in-one checkpoint. Flux, SD3.5, Wan 2.x, HunyuanVideo, LTX and Qwen-Image come as a standalone transformer file plus separate text encoders and a VAE. Load Diffusion Model loads only that transformer and outputs a MODEL; the text encoders come from DualCLIPLoader or Load CLIP and the VAE from Load VAE.
The weight_dtype option decides how the weights sit in memory: default keeps the file precision (bf16/fp16), while fp8_e4m3fn and fp8_e5m2 halve the VRAM needed with a small quality cost. fp8_e4m3fn_fast enables faster fp8 matrix math on RTX 40 series cards. GGUF quantised files need the separate ComfyUI-GGUF loader instead.

Inputs

Name
Type
What it is
unet_name
COMBO
The model file from models/diffusion_models (models/unet on older installs).
weight_dtype
COMBO
default, fp8_e4m3fn, fp8_e4m3fn_fast or fp8_e5m2. fp8 options store the weights in 8 bits to fit smaller cards.

Outputs

Name
Type
What it is
MODEL
MODEL
The denoising network, ready for LoRA loaders, ModelSamplingFlux, guidance nodes and KSampler.
AD
Skip the setup: ComfyUI workflows preinstalled on the cloud
BitVector runs ready-made ComfyUI workflows on its own GPUs. No install, no missing nodes, no red boxes. Open it on your phone or laptop and generate in a minute.

How to use Load Diffusion Model

  1. Download the transformer file (for example flux1-dev.safetensors) into models/diffusion_models.
  2. Download the text encoders into models/text_encoders (clip_l and t5xxl for Flux) and the VAE into models/vae.
  3. Add Load Diffusion Model and pick the file; choose fp8_e4m3fn if you have 12 GB of VRAM or less.
  4. Add DualCLIPLoader for the text encoders and Load VAE for the VAE.
  5. Wire MODEL to KSampler, CLIP to CLIP Text Encode, VAE to VAE Decode, and use EmptySD3LatentImage for the latent.

Settings and tips

  • Flux Dev wants cfg 1.0 with Flux Guidance around 3.5; the normal negative prompt has no effect at cfg 1.
  • If the file is already an fp8 checkpoint, leave weight_dtype on default; converting again gains nothing.
  • T5 can be loaded in fp8 too (t5xxl_fp8_e4m3fn.safetensors) to save another 5 GB of memory.
  • Keep bf16 weights when you fine-tune or train LoRAs; use fp8 for generation only.
  • The node name was UNETLoader for years; searching "UNET" still finds it.

Troubleshooting Load Diffusion Model

ERROR: Could not detect model type

Why it happens
The file is not a diffusion transformer ComfyUI knows (for example a full checkpoint, a LoRA or a GGUF file placed in the diffusion_models folder).

How to fix it
Full checkpoints go through Load Checkpoint, LoRAs through Load LoRA and .gguf files through the Unet Loader (GGUF) node from the ComfyUI-GGUF pack. Update ComfyUI if the model family is newer than your install.

Flux output is a blurry mess or pure noise

Why it happens
The sampler settings come from an SD workflow: cfg above 1 without Flux Guidance, an Empty Latent Image instead of EmptySD3LatentImage, or a wrong VAE (SDXL VAE with Flux).

How to fix it
Use ae.safetensors as the VAE, EmptySD3LatentImage, cfg 1.0, sampler euler with scheduler simple or beta, 20-28 steps and a Flux Guidance node at 3.5.

torch.OutOfMemoryError when loading a 24 GB Flux file

Why it happens
The bf16 file needs about 24 GB of VRAM on its own; the text encoder adds 10 GB in fp16.

How to fix it
Switch weight_dtype to fp8_e4m3fn and load t5xxl in fp8. On 8 GB cards use a GGUF Q4 or Q5 file with the GGUF loader and add --lowvram.

fp8_e4m3fn_fast is slower or errors on my GPU

Why it happens
The fast path needs an RTX 40 series (Ada) or newer GPU and a recent PyTorch; older cards fall back or fail.

How to fix it
Choose fp8_e4m3fn without _fast on RTX 30 and older cards.

AD
Run this workflow from your phone
Every workflow on this page is preinstalled on BitVector with the models and custom nodes already in place. Pick one, type a prompt, done. Zero setup, nothing to download.

Questions about Load Diffusion Model

Where do I put the file, models/unet or models/diffusion_models?

Both work. diffusion_models is the current name; unet is kept for old installs and both folders are scanned.

Does this node load the text encoder?

No. Pair it with DualCLIPLoader (two encoders, Flux and SD3) or Load CLIP (one encoder, Wan and Hunyuan).

Can I use Load LoRA with it?

Yes. Load LoRA takes the MODEL from this node. For Flux LoRAs that only patch the model, LoraLoaderModelOnly avoids needing a CLIP input.

Related nodes

Load Checkpoint
ComfyUI core
Load Checkpoint (CheckpointLoaderSimple) opens a .safetensors or .ckpt model file and hands out the three parts every workflow needs: the diffusion MODEL, the CLIP text encoder and the VAE.
DualCLIPLoader
ComfyUI core
DualCLIPLoader loads two text encoders at once, for example clip_l plus t5xxl for Flux or clip_g plus t5xxl for SD3, and outputs one CLIP object for the prompt nodes.
Load VAE
ComfyUI core
Load VAE (VAELoader) loads a standalone VAE file from models/vae so a checkpoint with a missing or weak VAE decodes clean colours, and so split models like Flux and Wan get their decoder.
EmptySD3LatentImage
ComfyUI core
EmptySD3LatentImage creates the 16-channel empty latent that Flux, SD3 and SD3.5 need; it replaces Empty Latent Image in those workflows.
Flux Guidance
ComfyUI core
Flux Guidance (FluxGuidance) writes the guidance value into the conditioning that Flux Dev was distilled to expect, replacing cfg; 3.5 is the default and 2 to 5 the useful range.
AD
Tired of fixing nodes? Let the cloud do it
BitVector keeps hundreds of ComfyUI workflows installed, updated and tested on fast cloud GPUs. No Python, no CUDA errors, no VRAM limits. Works from any browser.

More ComfyUI nodes

CLIP Text Encode (Prompt)
ComfyUI core
CLIP Text Encode turns a text prompt into CONDITIONING using the model text encoder. One node holds the positive prompt, a second one the negative prompt.
ComfyUI Manager
ComfyUI-Manager
ComfyUI Manager is the extension that installs, updates and fixes custom node packs and models from inside the interface, resolves missing nodes in imported workflows and snapshots your setup.
KSampler
ComfyUI core
KSampler runs the denoising loop: it takes the model, prompts and a latent and produces the finished latent image, controlled by seed, steps, cfg, sampler, scheduler and denoise.
Save Image
ComfyUI core
Save Image writes the IMAGE tensor to ComfyUI/output as a PNG, with the whole workflow embedded in the file metadata so the picture can be dragged back into ComfyUI to restore the graph.
VAE Decode
ComfyUI core
VAE Decode converts the sampled LATENT into a pixel IMAGE with the VAE; VAE Decode (Tiled) does the same in tiles for very large images.
Empty Latent Image
ComfyUI core
Empty Latent Image creates the blank latent canvas (width, height, batch_size) that text-to-image sampling starts from; dimensions must be multiples of 8 and match the model family.