ComfyUI Node: Hunyuan Unified Generate V2
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
Hunyuan/V2
Inputs
model_name
- HunyuanImage-3-NF4
- HunyuanImage-3-INT8
- HunyuanImage-3
prompt STRING
resolution
- Auto (model predicts)
- 768x1360 (9:16 Portrait)
- 832x1248 (2:3 Portrait)
- 864x1216 (5:7 Portrait)
- 880x1184 (3:4 Portrait)
- 912x1152 (4:5 Portrait)
- 976x1072 (9:10 Portrait)
- 1024x1024 (1:1 Square)
- 1072x976 (10:9 Landscape)
- 1152x912 (5:4 Landscape)
- 1184x880 (4:3 Landscape)
- 1216x864 (7:5 Landscape)
- 1248x832 (3:2 Landscape)
- 1360x768 (16:9 Landscape)
- 912x1632 (9:16 HD)
- 992x1504 (2:3 HD)
- 1040x1456 (5:7 HD)
- 1056x1408 (3:4 HD)
- 1088x1376 (4:5 HD)
- 1168x1296 (9:10 HD)
- 1232x1232 (1:1 HD)
- 1296x1168 (10:9 HD)
- 1376x1088 (5:4 HD)
- 1408x1056 (4:3 HD)
- 1456x1040 (7:5 HD)
- 1504x992 (3:2 HD)
- 1632x912 (16:9 HD)
- 1152x2048 (9:16 Large)
- 1248x1888 (2:3 Large)
- 1296x1824 (5:7 Large)
- 1328x1776 (3:4 Large)
- 1376x1712 (4:5 Large)
- 1456x1616 (9:10 Large)
- 1536x1536 (1:1 Large)
- 1616x1456 (10:9 Large)
- 1712x1376 (5:4 Large)
- 1776x1328 (4:3 Large)
- 1824x1296 (7:5 Large)
- 1888x1248 (3:2 Large)
- 2048x1152 (16:9 Large)
num_inference_steps INT
guidance_scale FLOAT
seed INT
blocks_to_swap INT
vae_placement
- auto
- always_gpu
- managed
post_action
- keep_loaded
- soft_unload
- full_unload
enable_vae_tiling BOOLEAN
flow_shift FLOAT
reserve_vram_gb FLOAT
moe_drop_tokens BOOLEAN
vae_dtype
- bfloat16
- float32
force_reload BOOLEAN
Outputs
IMAGE
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
- Hunyuan 3 Generate (HighRes Efficient)
- Hunyuan 3 Generate (Large/Offload)
Other Hunyuan/V2 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.