Professional AI Interior Design Toolkit for ComfyUI. Custom Qwen-VL nodes with 4 design modes: Text-to-Design, Mood Board, Reference Control, and Room Cleaning. Includes 5 optimized nodes with advanced strength controls and 23 preferred aspect ratios.

ComfyUI-ArchAi3d-Qwen

Load two CLIP text encoders with memory management and execution order control.

[Parameters]
trigger: Connect to any output to force execution order.
keep_on_vram: Pin dual CLIP to GPU VRAM permanently. Protected from auto-eviction. If you change either CLIP, the old one is automatically unpinned.
use_dram: Check DRAM cache (CPU RAM) for previously loaded dual CLIP. Much faster than disk reload.
replace_cached: When switching CLIPs, evict this loader's previous CLIP from DRAM. Saves RAM.
device: Load CLIP on GPU (default) or CPU. Use CPU to save VRAM for diffusion model.
cache_to_local_ssd: RunPod only — copy to local NVMe for faster loading.
auto_free_vram: Before loading from disk, if free VRAM < threshold, unpin all models and free VRAM. Only triggers for different model (same model reuses cache).
min_free_vram_gb: VRAM threshold in GB for auto_free_vram.
auto_free_dram: Before loading from disk, if free RAM < threshold, clear DRAM cache. Only triggers on DRAM miss.
min_free_dram_gb: RAM threshold in GB for auto_free_dram.

[Recipes]
sdxl: clip-l, clip-g
sd3: clip-l + clip-g / clip-l + t5 / clip-g + t5
flux: clip-l, t5
hidream: t5 + llama (recommended)
hunyuan_image: qwen2.5vl 7b, byt5 small
newbie: gemma-3-4b-it, jina clip v2

ComfyUI Node: 📦 Load Dual CLIP (Triggered)

Category

Inputs

Outputs

Extension: ComfyUI-ArchAi3d-Qwen

More nodes in ComfyUI-ArchAi3d-Qwen

Other ArchAi3d/Loaders nodes

Run ComfyUI workflows without the setup