What the tool does
Generation by Reference analyzes your image (subject, pose, camera angle, lighting, color grade, environment) and produces similar, not identical photos. It keeps the feel of the reference — location, pose family, styling — while exploring natural variations so you can pick the strongest frame.
Great for: recreating a look in different takes, matching a feed’s aesthetic, building sets for carousels, and preparing shots for Face Swap to lock identity.
Interface tour
Upload Reference Images
Drop PNG/JPEG files (up to 1000). Use clean, well-lit photos with a clear subject.
Upload Face (General model only)
Upload a portrait of the face you want to apply to the generated images.Add a Prompt (optional)
Add details you want. Keep it concise.Additional Settings
Adjust extra settings depending on the selected model: enable pose or background preservation, choose speed vs quality, set Reference Strength, and optionally add LoRA to guide style or physique.
Start Generation
Launch the batch. The per-image credit cost appears next to the button.
Models (General vs SDXL)
Image-to-Image currently supports two generation models.
Both models work with SFW and NSFW content, but they behave differently and expose different controls.
General model
The General model is faster and more flexible for everyday image-to-image workflows.
Supports Face Upload (optional face replacement during generation)
Supports Pose Preservation — keeps the pose from the reference image, with an option to preserve the original background or replace it; when disabled, the model freely reinterprets the pose
Allows stronger transformations from the reference
Works well for lifestyle shots, UGC scenes, casual photos, and quick iterations
Produces realistic, natural-looking images with high overall image quality
Recommended when:
You want speed, flexibility, pose control, high-quality realistic results, or to apply a specific face during generation.
Result examples:
reference
Keep Pose: ON · Swap Background: OFF Keep Pose: ON · Swap Background: ON
Keep Pose: OFF · Swap Background: OFF
SDXL model
The SDXL model is more focused on NSFW content generation, with stronger handling of body anatomy, proportions, and realistic figure shapes.
Does not support face upload
Uses a more constrained transformation logic
Produces cleaner skin, better proportions, and more consistent lighting
Supports Fast and Quality modes, allowing you to balance generation speed and visual fidelity
Includes additional controls such as Reference Strength — lower values allow the model to reinterpret the scene more freely
Supports LoRA models, which can be used to introduce specific body shapes, proportions, or complex anatomical features; LoRA strength can be adjusted for finer control
Recommended when:
You need more pronounced body shapes, better anatomical detail, and higher-quality NSFW generation, especially for body-focused scenes where figure accuracy and proportions matter more than strict reference preservation.
Result examples:
reference
Reference Strength: Max 1.5 · LoRA: OFF Reference Strength: 0.9 · LoRA: ON
Choosing the right model
Need pose preservation or the ability to keep/replace the background → General
Need face replacement during generation → General
Need better body anatomy, pronounced shapes, or NSFW-focused content → SDXL
Need fast experimentation and flexible transformations → General
Need detailed body rendering and anatomically accurate figures → SDXL
Quick start
Upload one or more clean reference images with a clear subject and good lighting.
Choose the appropriate generation model (General or SDXL) based on your task.
Adjust Reference Strength to control how closely the result follows the reference
(higher = closer to the original, lower = more creative freedom).(Optional) Add up to 3 LoRA models to influence body shape, style, or proportions, and fine-tune their strength as needed.
(Optional) Add short prompts to refine lighting, mood, or details.
Click Start Generation.
Review the completed results, select the best images, then Download them or Send them to another tool for further work.
Working with results
Use the checkboxes on thumbnails to Select/Deselect.
Download Selected / Download All to export a ZIP.
Send to another tool to continue the pipeline (Upscaler, Face Swapping, Generator by Ref, Video Generator, Carousel).
Retry Failed appears automatically if any frames mis-rendered.
Speed & quality flows
Fastest: Upscale + Face Swap flow — runs both in one pass on your selections for the cleanest final look.
Fully automated: Generation by Ref + Upscale + Face Swap flow — generates, upscales, and swaps faces automatically so every output is ready to publish with no tool hopping.
Best practice: Face Swap is most reliable as the final step. If the face must remain unchanged while enlarging, use Face-Safe Upscale.
Pro tips
Quality in → quality out. Choose references with sharp faces, simple backgrounds, and consistent light.
Batch for choice. Generate 8–10 variations per reference to find a hero frame.
Use LoRAs for physique/style. You don’t need a reference with a perfectly consistent body — SDXL + LoRAs will guide it.
FAQ
Do I need physique-consistent references?
No. Use SDXL with LoRAs to shape body type; the reference anchors pose/scene/mood.
How close will the results be to my reference?
Tune Reference Strength: 0.6–0.8 for creative range, 0.85–0.95 for close adherence.
Can I use LoRAs here?
Yes, up to 3 at once. Keep each at 0.6–0.9 to minimize artefacts.
What if the face isn’t the one I need?
Run Face Swap as the final step, or use the combined flow so images come out upscaled and face-swapped automatically.
Is the license commercial?
Yes — outputs are royalty-free for commercial use.
Troubleshooting
Identity feels off vs. reference: raise Reference Strength slightly or Face Swap the selected frames.
Anatomy/clothing glitches: lower LoRA strengths by 0.2, simplify prompts, re-run.
Soft/“plastic” detail: route selects to Upscaler.
Batch inconsistency: lock aspect ratio and seeds; avoid changing lighting/camera terms mid-series.
Need help choosing the right flow for your shoot? Ping the chat bubble or email [email protected].