ComfyUI Node: Hunyuan 3 Generate (Low VRAM Budget)

Authored by EricRollei

Created

Updated

64 stars

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)
  • 720x1280 - Portrait 720p (0.9MP)
  • 864x1152 - Portrait 3:4 (1.0MP)
  • 1024x1024 - Square 1K (1.0MP)
  • 1152x864 - Landscape 4:3 (1.0MP)
  • 1280x720 - Landscape 720p (0.9MP)
  • 1080x1920 - Portrait 1080p (2.1MP)
  • 1200x1600 - Portrait 3:4 (1.9MP)
  • 1440x1440 - Square 1.5K (2.1MP)
  • 1600x1200 - Landscape 4:3 (1.9MP)
  • 1920x1080 - Landscape 1080p (2.1MP)
  • 1440x2560 - Portrait 2K (3.7MP)
  • 1536x2048 - Portrait 3:4 (3.1MP)
  • 2048x2048 - Square 2K (4.2MP)
  • 2048x1536 - Landscape 4:3 (3.1MP)
  • 2560x1440 - Landscape 2K (3.7MP)
  • 2160x3840 - Portrait 4K (8.3MP)
  • 3072x3072 - Square 3K (9.4MP)
  • 3840x2160 - Landscape 4K (8.3MP)
  • 4096x4096 - Square 4K (16.8MP)
guidance_scale FLOAT
offload_mode
  • smart
  • always
  • disabled
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
gpu_budget_gb FLOAT

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

View Nodes

Looking for a different node?

More nodes in Comfy_HunyuanImage3

Other HunyuanImage3 nodes

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.

Learn more