ComfyUI / Workflow template
Bring a compatible character or style LoRA into Z-Image Turbo and shape a look for your NSFW gallery. Keep the adapter, strength and prompt together on your ComfyUI canvas, then save the images you want to develop.
Import the JSON, select your credentials and fill the required inputs before running.
Images with a chosen adapter’s influence, useful for a repeatable character look, an illustrated gallery or a different visual treatment for your NSFW project.
How the workflow runs
LoRA URL + scale
Trigger + scene prompt
Z-Image Turbo LoRA
SaveImage
NSFW / Character / Style
Build an original adult character for illustrated galleries, character cards or visual novel key art. A compatible style LoRA gives you another way to explore linework and finish alongside your prompt.
What to change first
Choose a LoRA made for Z-Image Turbo, include its trigger wording and compare one scene before adding another adapter.
Create a recognizable male character across relaxed portraits, silk-shirt editorials and night-out looks. Keep a few signature traits so the gallery feels like one creator rather than a collection of unrelated faces.
What to change first
Keep the same reference and hair description. Change lighting or wardrobe first, then try a different framing.
Give a recurring character a complete editorial story: window-light portraits, an evening look and a late-night balcony. Use four scenes to find a direction, then expand the strongest look into a larger set.
What to change first
Reuse the original portrait for each scene. Change the wardrobe and location; keep facial details and hair consistent.
Workflow tutorial
Import the JSON after installing the official SpicyAPI node package. Enter your key in Settings → SpicyAPI. This graph does not load a local model checkpoint or attach a local CLIP connection. Set a positive Max cost per run before queuing.
Choose a LoRA made for the supported Z-Image Turbo base. Use a reachable download link to the weight file, not a model gallery page or a link that requires your browser login. A Qwen, FLUX or Z-Image Base adapter is a different base.
Replace the LoRA URL placeholder with a direct public .safetensors link in SpicyAPI_LoRA and start scale at 1. Keep its output connected to the model’s loras input. This starter has one adapter; the endpoint accepts up to three.
Include the adapter author’s trigger wording when required, followed by your adult character, outfit, composition and light. Start with one adapter so you can see its effect before stacking more.
Queue a small test and save it. Keep the prompt and other settings steady when trying another scale; if the style overwhelms the face or composition, reduce the scale rather than adding more adapters.
Creative example. Adapt it to your own fictional adult character and source image.
An original adult anime character, age 30, with short silver hair and emerald eyes, wearing an elegant dark green evening outfit beside a jazz lounge window. Confident expression, crisp illustrated linework, cinematic night lighting, detailed fabric.Try this directionReference editing starts with Qwen Image 2.1; new concepts start with Z-Image Turbo. For a more specific NSFW style, explore compatible LoRA models and the Spicy collection before scaling your batch.
Each queued result is a task on the selected LoRA image endpoint. Read that endpoint’s current price and accepted settings before comparing several scales. A new scale or prompt creates another generation; save the best files instead of expecting a later rerun to reproduce them exactly.
Open the exact download URL and confirm that it returns the weight file without a login. Check the adapter’s base model and the connection into loras.
Check the trigger wording and compatibility first. If it loads but dominates the result, lower the scale and compare one change at a time.
LoadImage
Describe one edit
Qwen reference edit
SaveImage
ComfyUI
Outfit variants, scene changes and character frames
An edited image saved by SaveImage
Open workflowScene prompt
Z-Image Turbo
Image Upscaler
SaveImage
ComfyUI
Gallery covers, character portraits and larger delivery files
An upscaled image saved in ComfyUI
Open workflowDownload the template or try the same model in the Playground before connecting the full workflow.