Self-hosted n8n / Workflow template
Send /image and a scene description from your allowed Telegram chat. Your configured reference portrait anchors the edit; Qwen Image 2.1 makes the new look and the bot sends the finished image back.
Import the JSON, select your credentials and fill the required inputs before running.
A quick way to request a balcony portrait, a new outfit or a scene preview without opening your editing canvas. One message makes one image; your character reference stays in the workflow.
How the workflow runs
Telegram /image
Allowed chat check
Quote + reference edit
SendPhoto result
NSFW / Character / Style
Request a new character scene from Telegram with /image: a different outfit, a new room or a mood for your next story. The configured portrait stays in the workflow while each message supplies the new scene.
What to change first
Set the allowed chat and reference once. Keep each request focused on one scene; this template returns an image, not a text conversation.
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.
Explore a character’s wardrobe without rebuilding the entire scene: a fitted evening look, a themed costume or a different fabric treatment. Reference editing lets you compare the creative change against the original.
What to change first
Describe the garment, color and fabric explicitly. Keep pose and background steady for the first comparison.
Workflow tutorial
Import the inactive workflow into self-hosted n8n. Select your Telegram credential in both Telegram Trigger and SendPhoto, and the same SpicyAPI credential in Generate Character and Get Character Result.
Fill the single allowedChatId with your private chat’s ID. Keep enabled false until the reference, spending limit and output settings are ready.
Set referenceImageUrl to a reachable HTTPS portrait. Prepare Command combines the scene with a shared character instruction and complete-clothing fashion wording; adapt that wording to your own creative direction. This template uses the configured portrait rather than a newly uploaded photo.
Set maxCostUsd to a positive per-image limit up to 0.10 USD, then set enabled to true and activate the configured workflow when ready. Send /image followed by a specific scene, such as a café portrait with a cream sweater.
Get Character Result waits up to 300 seconds and downloads the completed image; only ready files go to SendPhoto. A needs_review result stays in the n8n execution. Task → Get its taskId before another attempt, or inspect the saved execution and console if no ID was recorded.
Creative example. Adapt it to your own fictional adult character and source image.
/image a quiet hotel balcony at dusk, navy satin jacket, warm lamp light, chest-up portraitTry 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 accepted /image message can submit one image-edit task after the quote check. A second scene request is another task, even if it uses the same portrait. Choose a per-message ceiling using the current Qwen editing price and leave the gate off when you do not want new requests.
Check workflow activation, enabled, allowedChatId and the /image command. Messages from another chat or with another command are deliberately outside this template’s path.
Keep the download enabled and the SendPhoto binary property at data. Do not put the temporary result URL into a field configured for a binary file.
Reference + scenes
One item per scene
Quote + Qwen edit
Download each image
n8n Cloud + self-hosted
Recurring character sets and NSFW creator galleries
4, 8 or 12 separate image results
Open workflowRead todo rows
Limit to four
Generate + download
Update the same rows
n8n Cloud + self-hosted
Prompt libraries, character concepts and small creator batches
Image files plus row-level status and result links
Open workflowDownload the template or try the same model in the Playground before connecting the full workflow.