ComfyUI Node: Z-Image Turbo LoRA Stack
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
loaders/Z-Image
Inputs
model MODEL
lora_1
- None
strength_1 FLOAT
enabled_1 BOOLEAN
fuse_qkv_1 BOOLEAN
lora_2
- None
strength_2 FLOAT
enabled_2 BOOLEAN
fuse_qkv_2 BOOLEAN
lora_3
- None
strength_3 FLOAT
enabled_3 BOOLEAN
fuse_qkv_3 BOOLEAN
lora_4
- None
strength_4 FLOAT
enabled_4 BOOLEAN
fuse_qkv_4 BOOLEAN
lora_5
- None
strength_5 FLOAT
enabled_5 BOOLEAN
fuse_qkv_5 BOOLEAN
lora_6
- None
strength_6 FLOAT
enabled_6 BOOLEAN
fuse_qkv_6 BOOLEAN
lora_7
- None
strength_7 FLOAT
enabled_7 BOOLEAN
fuse_qkv_7 BOOLEAN
lora_8
- None
strength_8 FLOAT
enabled_8 BOOLEAN
fuse_qkv_8 BOOLEAN
lora_9
- None
strength_9 FLOAT
enabled_9 BOOLEAN
fuse_qkv_9 BOOLEAN
lora_10
- None
strength_10 FLOAT
enabled_10 BOOLEAN
fuse_qkv_10 BOOLEAN
Outputs
MODEL
Extension: Comfyui-ZiT-Lora-loader
Architecture-aware LoRA loader for Z-Image Turbo (Lumina2) in ComfyUI. Fixes silent key mismatches by auto-fusing separate Q/K/V into Z-Image's fused QKV format and remapping output projections.
Authored by capitan01R
Looking for a different node?
More nodes in Comfyui-ZiT-Lora-loader
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.