FLUX PuLID
Keep your face, any scene
Identity-locked generation. Upload 1–3 photos of yourself; place yourself in any scene, outfit, or style without losing facial likeness.
Cost per image
5 credits
Free renders
~20 on free plan
Watermark
None — even free
Animate to video
1-click, 5–10s
What is FLUX PuLID?
Identity-locked generation. Upload 1–3 photos of yourself; place yourself in any scene, outfit, or style without losing facial likeness.
FLUX PuLID is an identity-locking AI image model: upload 1–3 reference photos of yourself or your subject and it generates new scenes — portraits, lifestyle shots, product mockups, professional headshots, character illustrations — with that specific face preserved across every render, regardless of outfit, setting, camera angle, or lighting. The model encodes a face from reference photos into a high-dimensional embedding that travels with every subsequent generation. On FluxNote, those embeddings are stored privately to your account, never used to train any model, and can be purged on request at any time.
FLUX PuLID requires 1–3 reference photos of the subject to generate an identity embedding. Clear, well-lit frontal photos produce the most stable identity lock; sunglasses, heavy filters, or extreme side angles reduce fidelity. Generation time is 12–20 seconds per image. Once the identity is locked, the reference photos are no longer needed in the prompt — FLUX PuLID recalls the face from the stored embedding. FluxNote supports multiple saved identities so creators can maintain different subjects (personal brand, clients, characters) without re-uploading references each session.
On FluxNote, FLUX PuLID costs 5 credits per image. The free plan includes 100 credits per month — enough for 20 FLUX PuLID renders with no credit card and no watermark. Paid plans (from $9/month) scale up to 15,000 credits without changing how the model or the interface works. FLUX PuLID sits alongside 18 other image models in the same dashboard; switching to a different model for a different job is a single click, no separate subscription required.
Every FLUX PuLID output has a one-click animate button. FluxNote sends the still to one of its AI video models — Sora 2 Pro, Veo 3, Kling 3.0, Runway Gen-4, or Seedance 2.0 — and returns a 5–10 second clip. This image-to-video workflow is particularly useful for ad creatives (static images animate well for story and feed placements), social content (a single FLUX PuLID image can become a TikTok, Reel, and YouTube Short), and product showcases (slow camera moves around a product image that isn't technically a 3D model).
For most workflows, FLUX PuLID works best as part of a multi-model pipeline: generate concepts fast with FLUX Schnell or Gemini Flash 2.5 at 1–4 credits per image, switch to FLUX PuLID for the final render, then run the result through FLUX Kontext Edit for last-mile corrections, or Nucleus Image if you need a 2× or 4× upscale for print. All of these models are available under the same FluxNote subscription — there's no additional charge to access other models.
Spec sheet
Hard numbers — what FLUX PuLID accepts and what it produces.
Resolution
Up to 1536×1536
Generation time
12–20 seconds
Aspect ratios
1:1, 4:5, 9:16, 16:9
Inputs
1–3 reference photos + text prompt
Real outputs from FLUX PuLID
7 samples generated by FluxNote users. Hover any image to read the prompt.
Create a realistic vertical social media ad video in 9:16 format based on the uploaded image. Story: A cute small cream-colored cat is resting in a stylish window-mounted cat bed in a bright, sunny home. At the start of the video, the cat slowly opens its eyes, gently stretches, and comfortably adj
Professional character design reference sheet, Korean manhwa art style, clean layout: Main character: Daniel Archer (Current/Stagnant Version) 32 year old Caucasian American male, software developer Physical appearance: - Slim but out of shape build, slight gut, poor posture, 5'10" height - Dark b
Mereka berdiri dan saling berpelukan, lalu bergandeng tangan dan berjalan perlahan
Mereka berdiri dan saling berpelukan, lalu bergandeng tangan dan berjalan perlahan
Say: mom...mom! I'm scared
Animate the character in the uploaded image without changing their appearance or the background. Keep the face, proportions, lighting, colors and environment exactly the same. Only add natural, realistic facial animation and lipsync to match the spoken English text. No head replacement, no style cha
FLUX PuLID: strengths & limitations
An honest picture of what FLUX PuLID does well — and where it doesn't. Use this to decide whether to pick FLUX PuLID or one of FluxNote's 18 other image models for a given job.
Strengths
- ●Locks facial identity from just 1–3 reference photos — no fine-tuning required.
- ●Maintains likeness across wildly different scenes, outfits, and lighting setups.
- ●Strong on subtle expression control (smiling, serious, looking left, etc.).
Limitations
- ●Needs at least one clear front-facing reference photo to lock identity reliably.
- ●Glasses, beards, and accessories can occasionally drift between renders — re-prompt with the detail explicit.
3 ways creators use FLUX PuLID
Real-world workflows we see most often in the FluxNote dashboard.
LinkedIn headshot library
Scenario:You need 6 polished professional headshots in different settings — office, industrial, exterior, casual.
Walkthrough:Upload 2 selfies, prompt one scene per generation ('navy blazer in a minimalist office', 'on factory floor with hard hat'), batch and download.
Personal-brand content engine
Scenario:Founder building a Twitter/LinkedIn presence wants 30 days of visually consistent post imagery.
Walkthrough:Lock your face once, generate 30 thematically-linked scenes (whiteboard, coffee shop, conference stage) — every post stays visually 'you'.
Wedding/event photo mockups
Scenario:You want to see a styling concept (suit, dress, venue) before booking the photographer.
Walkthrough:Upload your face, describe the venue and outfit, render variations, share with the planner — costs cents instead of hours.
Prompt examples that work with FLUX PuLID
Copy-paste any of these prompts into the FLUX PuLID model to get a result close to the example.
Professional headshot
{me} as a 35-year-old executive, navy blazer, minimalist office, soft natural light from large window, 85mm portrait lensLifestyle content
{me} laughing while cooking pasta in a Brooklyn brownstone kitchen, late afternoon golden light, candid documentary feelConceptual portrait
{me} in a black turtleneck, dramatic single key-light, deep shadow background, editorial portrait, Annie Leibovitz styleHow to get the best results from FLUX PuLID
Prompt strategies that consistently improve output quality — based on how FLUX PuLID was trained and what it responds to.
Be specific about lighting
Instead of "product photo", try "product on white marble, soft diffused window light from the left, slight shadow on the right, 85mm lens perspective". Lighting direction and quality are the single biggest driver of FLUX PuLID's realism.
Name the camera or lens
"35mm film grain", "85mm portrait lens", "macro lens close-up", "wide-angle environmental shot" — FLUX PuLID was trained on a corpus that includes photography metadata. Camera/lens references activate a different distribution of outputs than generic prompts.
Describe what's NOT in the frame
Adding "no text, no watermark, no border, clean background" prevents FLUX PuLID from adding visual clutter that wasn't requested. Negative constraints are especially useful for product photography and editorial portraits.
Use aspect ratio to guide composition
FLUX PuLID adapts composition to the requested aspect ratio. For a 9:16 vertical, it naturally produces portrait-style framing. For 16:9, it composes for landscape. Choosing the right ratio before prompting — rather than cropping after — gives you better compositions and less wasted generation.
Iterate on the seed before changing the prompt
When FLUX PuLID produces a near-miss result, try regenerating with a different seed before rewriting the prompt. 80% of the time, the issue is randomness, not prompt direction. Changing the seed with the same prompt often produces the version you were looking for.
Upload frontal reference photos for best identity lock
Clear, well-lit frontal photos produce the strongest identity embedding. Avoid sunglasses, masks, extreme angles, or heavily filtered selfies as reference inputs — these reduce the model's ability to reconstruct the face accurately across new generations.
Describe the scene, not the face
Once FLUX PuLID has locked the identity from your reference photos, describe the new scene rather than re-describing the face: "in a professional LinkedIn headshot setting, navy blazer, neutral background, confident expression". The identity travels automatically — you're directing the scene.
FLUX PuLID vs other FluxNote models
Quick reference for picking the right model — every alternative below ships in the same FluxNote subscription.
vs FLUX FaceSwap
FLUX FaceSwap swaps a face onto an existing image; FLUX PuLID generates a new image around your face.
vs Avatar
Avatar produces stylized characters; FLUX PuLID produces photoreal you.
How to generate with FLUX PuLID
Four steps from prompt to publish-ready output. Total time: under 20 seconds.
Upload reference photos
Sign in to FluxNote (free, no card) and upload 1–3 clear photos of yourself or your subject. FLUX PuLID embeds these privately to lock identity for every render — your reference photos are never used to train any model and you can purge them at any time from settings.
Write your prompt
Describe the image in plain English. FLUX PuLID responds best to specific details — subject, setting, lighting, lens, mood. It's tuned for headshots, personal branding, avatars, but it handles general-purpose prompts too. If your prompt is short, FluxNote's built-in prompt assistant can expand it for you in one click.
Pick aspect ratio and style
Choose 1:1, 9:16, 16:9, 4:5, or 3:2 to match your destination — TikTok, Instagram, YouTube thumbnail, blog hero, print. Add an optional style preset (cinematic, anime, photoreal, painterly, etc.) to bias the output. Premium aspect ratios like 21:9 unlock on the Pro plan.
Generate, refine, animate
Hit generate. FLUX PuLID typically renders in 12–20 seconds. Iterate on the prompt or seed to dial it in, then export full-resolution PNG with no watermark. Want it animated? Click the animate button to turn the still into a 5–10 second video clip in the same dashboard, no separate tool required.
Why creators pick FluxNote for FLUX PuLID
FLUX PuLID is one of 19 image models on FluxNote. One subscription unlocks them all.
One subscription covers FLUX PuLID plus 18 other AI image models — FLUX 2 Pro, FLUX PuLID, FLUX Kontext Edit, Seedream 3, Gemini Flash 2.5, FLUX Schnell, and more. No per-model paywalls and no separate logins for each provider.
100 free credits per month, no credit card required to start. FLUX PuLID costs 5 credits per image — that's around 20 free renders on the free plan alone.
Zero watermark on every plan including free. Your FLUX PuLID images export as clean full-resolution PNG, ready for paid social, print, or anywhere else.
Animate any FLUX PuLID output into a 5–10 second video clip with one click. Useful for ads, story posts, reel openers, and YouTube thumbnails — the animation cost is metered separately and starts at 6 credits.
Built-in prompt assistant, batch generation, image-to-image variations, and a reusable prompt library. You don't need to memorize prompt syntax — paste a rough idea and FluxNote refines it.
Reusable seed and style controls — lock the visual direction once, regenerate variants without losing it. FLUX PuLID respects seed control like the underlying API does.
Private by default. Outputs are visible only to your account unless you publish them to the showcase. We never sell or share your prompts and reference images.
FLUX PuLID FAQ
The 10 questions creators ask most often before switching to FLUX PuLID.
Is FLUX PuLID free on FluxNote?+
Yes — every FluxNote plan including the free tier (100 credits/month) can generate with FLUX PuLID. Each generation costs 5 credits, so the free tier covers around 20 renders per month with no credit card required.
What is FLUX PuLID best for?+
Headshots, Personal branding, Avatars. Identity-locked generation. Upload 1–3 photos of yourself; place yourself in any scene, outfit, or style without losing facial likeness. If your project is specifically commercial-print or hero-creative work, you may want to pair it with one of FluxNote's premium models (FLUX 2 Max, Imagen 4 Fast, Seedream 4) for the final render.
Does FLUX PuLID add a watermark?+
No. FluxNote does not watermark any output, on any plan, including free. Every FLUX PuLID image exports as a clean full-resolution PNG that you can use commercially without attribution.
Can I use FLUX PuLID commercially?+
Yes. FluxNote grants commercial usage rights on outputs from every model including FLUX PuLID. You can use the images in ads, products, books, and merchandise. As with any AI generation, double-check that the prompt and output don't reproduce protected likenesses or trademarks.
What input does FLUX PuLID need?+
1–3 reference photos + text prompt. Identity models like FLUX PuLID need 1–3 clear reference photos plus your text prompt.
Can I turn a FLUX PuLID image into a video?+
Yes — every FLUX PuLID output has a one-click animate button. FluxNote will generate a 5–10 second video clip from your still using one of the AI video models (Runway Gen-4, Kling, Sora 2 Pro, Veo 3, Seedance). Pick the model from the animate dropdown; cost starts at 6 credits per clip.
What resolutions can FLUX PuLID export?+
Up to 1536×1536. Free plan exports the same resolution as paid plans — there is no quality gating. If you need print-grade resolution, run the result through Nucleus afterwards to upscale 2× or 4× without losing detail.
Is my data private?+
Yes. Reference photos and prompts are visible only to your account. We do not sell prompts, do not train on your inputs, and you can delete generated images at any time from your library. Identity-locked models (FLUX PuLID) embed reference photos privately and you can purge embeddings on request.
FLUX PuLID vs other AI image models — when should I pick it?+
Use FLUX PuLID when headshots, personal branding, avatars matter most. Compared to FLUX FaceSwap, flux faceswap swaps a face onto an existing image; flux pulid generates a new image around your face. Compared to Avatar, avatar produces stylized characters; flux pulid produces photoreal you. For an everyday default, most creators pick FLUX Schnell or Gemini Flash 2.5; for hero work, FLUX 2 Max or Seedream 4; for identity, FLUX PuLID; for targeted edits, FLUX Kontext Edit.
Do I need to install anything?+
No. FluxNote runs in any modern browser — Chrome, Firefox, Safari, Edge — on desktop and mobile. There is no install, no GPU requirement, and no waiting in line. Your library, prompts, and outputs sync across devices automatically.
More Identity Lock models
Same category, different strengths.
Other models on FluxNote
Your first viral video is 90 seconds away.
Type a topic. AI writes, voices, captions, and edits.
You download a 1080p video — yours to post anywhere.
Already 100,000+ creators won't tell you this is their secret.