ComfyUI Node
BD Lotus-2 Model Loader
Load Lotus-2 (FLUX.1-dev + LoRAs + LCM bridge) for depth or normal estimation. Diffusion-based, SOTA-quality monocular geometry prediction. FLUX.1-dev is loaded from HF cache (~24 GB). Lotus-2 weights (~1.5 GB depth or ~2.9 GB normal core+sharpener) auto-download to ComfyUI models/lotus2/{task}/ if missing. Reuse the loaded model across multiple Predict calls — first load is slow, subsequent same-task calls hit the in-memory cache.
BD Lotus-2 Model Loader
- model
◄taskdepth►
◄dtypebf16►
◄deviceauto►
◄flux_repo_idblack-forest-labs/FLUX.1-dev►
◄lotus2_weights_dir►
◄cpu_offloadfalse►
Category🧠BrainDead/Depth
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| task | COMBO | depth | Which Lotus-2 LoRA pair to load. depth = ~1.5 GB, normal = ~2.9 GB (different LoRA rank). |
| dtype | COMBO | bf16 | Inference precision. bf16 recommended on Blackwell/H100. |
| device | COMBO | auto | 3 options: auto, cuda, cpu |
| flux_repo_idopt | STRING | black-forest-labs/FLUX.1-dev | HF repo id for the FLUX.1-dev base. Loaded via HF cache (HF_HOME env). Override only if you have a fork. |
| lotus2_weights_diropt | STRING | Override directory containing the three Lotus-2 weight files. Default: <ComfyUI models dir>/lotus2/{task}/ | |
| cpu_offloadopt | BOOLEAN | false | Enable diffusers model CPU offload. Each pipeline module (transformer / VAE / text encoders) lives on CPU and moves to GPU only when needed. Peak VRAM drops from ~35 GB to ~27 GB (largest single module + activations) at the cost of ~1.5x slower inference per call. Turn on when running Lotus-2 alongside other large models (Qwen-Image-Edit, FLUX gen, etc). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| model | LOTUS2_MODEL | — |