ComfyUI Node: Hunyuan 3 Generate
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 HUNYUAN_MODEL
prompt STRING
seed INT
steps INT
resolution
- Auto (model default)
- 768x1344 - 9:16 (1.0MP)
- 768x1280 - 5:8 (1.0MP)
- 832x1216 - 2:3 (1.0MP)
- 896x1152 - 3:4 (1.0MP)
- 896x1088 - 4:5 (1.0MP)
- 1024x1024 - 1:1 (1.0MP)
- 1088x896 - 5:4 (1.0MP)
- 1152x896 - 4:3 (1.0MP)
- 1216x832 - 3:2 (1.0MP)
- 1280x768 - 8:5 (1.0MP)
- 1344x768 - 16:9 (1.0MP)
- 1088x1856 - 9:16 (2.0MP)
- 1088x1792 - 5:8 (1.9MP)
- 1152x1728 - 2:3 (2.0MP)
- 1216x1664 - 3:4 (2.0MP)
- 1280x1600 - 4:5 (2.0MP)
- 1408x1408 - 1:1 (2.0MP)
- 1600x1280 - 5:4 (2.0MP)
- 1664x1216 - 4:3 (2.0MP)
- 1728x1152 - 3:2 (2.0MP)
- 1792x1088 - 8:5 (1.9MP)
- 1856x1088 - 16:9 (2.0MP)
- 1280x2304 - 9:16 (2.9MP)
- 1344x2176 - 5:8 (2.9MP)
- 1408x2112 - 2:3 (3.0MP)
- 1472x1984 - 3:4 (2.9MP)
- 1536x1920 - 4:5 (2.9MP)
- 1728x1728 - 1:1 (3.0MP)
- 1920x1536 - 5:4 (2.9MP)
- 1984x1472 - 4:3 (2.9MP)
- 2112x1408 - 3:2 (3.0MP)
- 2176x1344 - 8:5 (2.9MP)
- 2304x1280 - 16:9 (2.9MP)
guidance_scale FLOAT
post_action
- keep_loaded
- soft_unload_to_cpu
- full_unload
enable_prompt_rewrite BOOLEAN
rewrite_style
- none
- en_recaption
- en_think_recaption
api_url STRING
model_name STRING
Outputs
IMAGE
STRING
STRING
*
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 Loader (Multi-GPU BF16)
- Hunyuan 3 Force Unload (Nuclear)
- Hunyuan 3 Loader (Full BF16 GPU)
- Hunyuan 3 Loader (Full BF16)
- 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.