SDXL Turbo txt2img (ComfyUI Workflow)
ComfyUI Workflowby mm-team · 5/18/2026
SDXL Turbo text-to-image workflow for ComfyUI. Fast single-step generation. Tested on RTX 3080 (10 GB VRAM). Generates 1024x1024 in ~1s.
↓ 35 downloads ♥ 11 likes ⚡ 28 boots cuda
config.json
{
"server_type": "comfyui-workflow",
"hardware_type": "cuda",
"comfyui_version": ">=0.2.0",
"workflow": {
"3": {
"class_type": "KSampler",
"inputs": {
"seed": 42,
"steps": 1,
"cfg": 1,
"sampler_name": "euler_ancestral",
"scheduler": "normal",
"denoise": 1,
"model": [
"4",
0
],
"positive": [
"6",
0
],
"negative": [
"7",
0
],
"latent_image": [
"5",
0
]
}
},
"4": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "sd_xl_turbo_1.0_fp16.safetensors"
}
},
"5": {
"class_type": "EmptyLatentImage",
"inputs": {
"width": 1024,
"height": 1024,
"batch_size": 1
}
},
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "a photo of a cat",
"clip": [
"4",
1
]
}
},
"7": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "",
"clip": [
"4",
1
]
}
},
"8": {
"class_type": "VAEDecode",
"inputs": {
"samples": [
"3",
0
],
"vae": [
"4",
2
]
}
},
"9": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "mm_output",
"images": [
"8",
0
]
}
}
},
"required_models": [
"sd_xl_turbo_1.0_fp16.safetensors"
],
"required_nodes": []
}