ComfyUI Node: Hunyuan Instruct Image Edit
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/Instruct
Inputs
model HUNYUAN_INSTRUCT_MODEL
image IMAGE
instruction STRING
bot_task
- image
- recaption
- think_recaption
seed INT
system_prompt
- dynamic
- en_unified
- en_recaption
- en_think_recaption
- en_vanilla
- none
align_output_size BOOLEAN
resolution
- Auto (model predicts)
- 512x2048 (1:4 Tall)
- 512x1984 (~1:4 Tall)
- 512x1920 (4:15 Tall)
- 512x1856 (~1:4 Tall)
- 512x1792 (2:7 Tall)
- 512x1728 (~1:3 Tall)
- 512x1664 (4:13 Tall)
- 512x1600 (8:25 Tall)
- 512x1536 (1:3 Portrait)
- 576x1472 (9:23 Portrait)
- 640x1408 (5:11 Portrait)
- 704x1344 (11:21 Portrait)
- 768x1280 (3:5 Portrait)
- 832x1216 (13:19 Portrait)
- 896x1152 (7:9 Portrait)
- 960x1088 (15:17 Portrait)
- 1024x1024 (1:1 Square)
- 1088x960 (17:15 Landscape)
- 1152x896 (9:7 Landscape)
- 1216x832 (19:13 Landscape)
- 1280x768 (5:3 Landscape)
- 1344x704 (21:11 Landscape)
- 1408x640 (11:5 Landscape)
- 1472x576 (23:9 Landscape)
- 1536x512 (3:1 Wide)
- 1600x512 (25:8 Wide)
- 1664x512 (13:4 Wide)
- 1728x512 (27:8 Wide)
- 1792x512 (7:2 Wide)
- 1856x512 (29:8 Wide)
- 1920x512 (15:4 Wide)
- 1984x512 (31:8 Wide)
- 2048x512 (4:1 Wide)
steps INT
guidance_scale FLOAT
flow_shift FLOAT
max_new_tokens INT
verbose INT
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
- Hunyuan 3 Generate (HighRes Efficient)
- Hunyuan 3 Generate (Large/Offload)
Other Hunyuan/Instruct 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.