ComfyUI Node: Hunyuan 3 Loader (Multi-GPU BF16)
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
HunyuanImage3
Inputs
model_name
- HunyuanImage-3
primary_gpu INT
reserve_memory_gb FLOAT
exclude_gpus STRING
info STRING
Outputs
HUNYUAN_MODEL
Extension: Comfy_HunyuanImage3
Professional ComfyUI custom nodes for Tencent's HunyuanImage-3.0 80B multimodal model, with multiple loading modes, smart memory management, large image generation with CPU offload, and optional prompt enhancement via LLM APIs.
Authored by EricRollei
Looking for a different node?
More nodes in Comfy_HunyuanImage3
- Hunyuan Cache Status V2
- Hunyuan Emergency Cleanup
- Hunyuan Empty Latent
- Hunyuan Generate with Latent
- Hunyuan 3 Clear Downstream Models
- Hunyuan 3 Force Unload (Nuclear)
- Hunyuan 3 Loader (Full BF16 GPU)
- Hunyuan 3 Loader (Full BF16)
- Hunyuan 3 Generate
- Hunyuan 3 Generate (HighRes Efficient)
- Hunyuan 3 Generate (Large/Offload)
- Hunyuan 3 Generate (Large Budget)
Other HunyuanImage3 nodes
- Hunyuan 3 Generate (Low VRAM)
- Hunyuan 3 Generate (Low VRAM Budget)
- Hunyuan 3 Generate (Telemetry)
- Hunyuan 3 GPU Info
- Hunyuan 3 Loader (INT8)
- Hunyuan 3 Loader (INT8 Budget)
- Hunyuan 3 Loader (NF4 Low VRAM+)
- Hunyuan 3 Loader (NF4)
- Hunyuan 3 Loader (88GB GPU Optimized)
- Hunyuan 3 Soft Unload (Fast)
- Hunyuan 3 Unload
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.