Load Flux.2 Models + LoRAs
Flux.2's loader plus a 16-slot LoRA chain — mostly for the Klein crowd
- model
- clip
- vae
If you're running Flux.2 and using LoRAs, you are almost certainly on Klein. The community's verdict on the dev tier - gorgeous, but 18–24GB even quantized and slower than molasses - pushed the actual day-to-day usage onto the 4B/9B Klein variants, and that's exactly the crowd that wants a LoRA stack without building a LoRA spaghetti graph. Load Flux.2 Models + LoRAs bundles the Flux.2 loader (UNet + single CLIP + VAE) and a 16-slot sequential LoRA stack into one node. Set lora_count, pick files, dial strengths, get model/clip/vae out the far side.
It's the Flux.2 counterpart of the pack's Load Flux.1 Models + LoRAs, and the reasoning is the same: LoRA chains in raw ComfyUI mean one LoraLoader node per LoRA, each with its own strength widgets, all wired in series. This collapses that into a panel.
How it works
The loader half wraps UNETLoader, CLIPLoader (type defaulted to flux2), and VAELoader, same as DiztraidoLoadFlux2Models. The LoRA half adds lora_count plus 16 slots of lora_name / strength_model / strength_clip. At execution it loads the base model, then applies the active LoRAs in slot order through ComfyUI's LoraLoader, feeding each result into the next - so slot order is application order. Empty slots and double-zero strengths are skipped. One difference from the Flux.1 variant worth noting: here the per-slot strength_clip defaults are set to 0.0 explicitly (the Flux.1 version's schema also ends up there, this one is just deliberate about it), which is the right starting point for Flux LoRAs.
The inputs that matter
unet_name,weight_dtype(fp8_e4m3fnis the sensible default),clip_name(single text encoder),type(leave onflux2),vae_name(pixel_space).lora_count- 0 to 16 active slots.lora_1…lora_16- file pickers frommodels/loras/.strength_model_N/strength_clip_N- defaults 1.0 / 0.0;strength_clipstays 0 for Flux.
Outputs: model, clip, vae.
How to install
Comes with Diztraido Nodes. ComfyUI Manager → search "Diztraido Nodes" → install diztraido-nodes → restart. Or:
cd ComfyUI/custom_nodes
git clone https://github.com/jadervasque/ComyUI-Diztraido.git
Restart, and it's under the Diztraido flux category. No extra dependencies; models and LoRAs come from your existing ComfyUI/models/ tree.
Common issues
The same trio of gotchas as every stacker: order matters (top slot applies first), a stack of 1.0-strength LoRAs is usually too hot - start around 0.6–0.8 each - and an empty lora_name dropdown means the file isn't in models/loras/. One Flux.2-specific reality check: Klein's distilled checkpoints are guidance-distilled and behave differently from dev (the community found the stock Flux2Scheduler sigmas, built for dev, need adjusting for Klein). That's a sampler concern, not this loader's, but it means if your Klein output looks off, the fix is in the sampler schedule, not your LoRA stack.
Inputs (54)
| Name | Type | Default | Description |
|---|---|---|---|
| unet_name | COMBO | 0 options: | |
| weight_dtype | COMBO | 4 options: default, fp8_e4m3fn, fp8_e4m3fn_fast, fp8_e5m2 | |
| clip_name | COMBO | 0 options: | |
| type | COMBO | 28 options: stable_diffusion, stable_cascade, sd3, stable_audio, mochi, ltxv, +22 | |
| vae_name | COMBO | 1 options: pixel_space | |
| lora_count | INT | 00–16 | — |
| lora_1 | COMBO | The name of the LoRA. | |
| strength_model_1 | FLOAT | 1.00-100–100 | — |
| strength_clip_1 | FLOAT | 0.00-100–100 | — |
| lora_2 | COMBO | The name of the LoRA. | |
| strength_model_2 | FLOAT | 1.00-100–100 | — |
| strength_clip_2 | FLOAT | 0.00-100–100 | — |
| lora_3 | COMBO | The name of the LoRA. | |
| strength_model_3 | FLOAT | 1.00-100–100 | — |
| strength_clip_3 | FLOAT | 0.00-100–100 | — |
| lora_4 | COMBO | The name of the LoRA. | |
| strength_model_4 | FLOAT | 1.00-100–100 | — |
| strength_clip_4 | FLOAT | 0.00-100–100 | — |
| lora_5 | COMBO | The name of the LoRA. | |
| strength_model_5 | FLOAT | 1.00-100–100 | — |
| strength_clip_5 | FLOAT | 0.00-100–100 | — |
| lora_6 | COMBO | The name of the LoRA. | |
| strength_model_6 | FLOAT | 1.00-100–100 | — |
| strength_clip_6 | FLOAT | 0.00-100–100 | — |
| lora_7 | COMBO | The name of the LoRA. | |
| strength_model_7 | FLOAT | 1.00-100–100 | — |
| strength_clip_7 | FLOAT | 0.00-100–100 | — |
| lora_8 | COMBO | The name of the LoRA. | |
| strength_model_8 | FLOAT | 1.00-100–100 | — |
| strength_clip_8 | FLOAT | 0.00-100–100 | — |
| lora_9 | COMBO | The name of the LoRA. | |
| strength_model_9 | FLOAT | 1.00-100–100 | — |
| strength_clip_9 | FLOAT | 0.00-100–100 | — |
| lora_10 | COMBO | The name of the LoRA. | |
| strength_model_10 | FLOAT | 1.00-100–100 | — |
| strength_clip_10 | FLOAT | 0.00-100–100 | — |
| lora_11 | COMBO | The name of the LoRA. | |
| strength_model_11 | FLOAT | 1.00-100–100 | — |
| strength_clip_11 | FLOAT | 0.00-100–100 | — |
| lora_12 | COMBO | The name of the LoRA. | |
| strength_model_12 | FLOAT | 1.00-100–100 | — |
| strength_clip_12 | FLOAT | 0.00-100–100 | — |
| lora_13 | COMBO | The name of the LoRA. | |
| strength_model_13 | FLOAT | 1.00-100–100 | — |
| strength_clip_13 | FLOAT | 0.00-100–100 | — |
| lora_14 | COMBO | The name of the LoRA. | |
| strength_model_14 | FLOAT | 1.00-100–100 | — |
| strength_clip_14 | FLOAT | 0.00-100–100 | — |
| lora_15 | COMBO | The name of the LoRA. | |
| strength_model_15 | FLOAT | 1.00-100–100 | — |
| strength_clip_15 | FLOAT | 0.00-100–100 | — |
| lora_16 | COMBO | The name of the LoRA. | |
| strength_model_16 | FLOAT | 1.00-100–100 | — |
| strength_clip_16 | FLOAT | 0.00-100–100 | — |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| model | MODEL | — |
| clip | CLIP | — |
| vae | VAE | — |