Model
.ai
memantau model AI terbuka

Disguise Drop LTX 2 / Wan2.1 14B FLF2V

8030°
Disguise Drop   LTX 2 / Wan2.1 14B FLF2V
Dicipta oleh
kabachuha
di Civitai
by kabachuha - Disguise Drop - LTX-2 / Wan2.1 14B FLF2V
Nota pencipta
When the mask falls off… who’s really inside? LTX-2 Disguise Drop! Remake of my very first Wan lora now for LTX-2! The sound effects take it to a new level! The LoRA brings the classic unzipping surprise cartoon effect where a character suddenly unzips their skin, revealing another character inside them all along! This time - compared to my other LTX-2 loras so far - thanks to calibrated LR scheduling, it has virtually no grayness and you can use it in image2video and first-last-frame2video modes alike! The workflows are embedded within the videos or you can use the .json file inside the Huggingface files folder at . It's the native workflow with KJ Nodes and VideoHelperSuite. The training recipe is exactly the same as for my previous one-hand-squish lora, except for the lowered rank to prevent overfitting. This lora converged in 3520 steps. The model was trained with Disguise drop. as the prefix, but you can simply describe the action in details. Wan 2.1 This Wan2.1 First-last-frame LoRA aims to replicate the weird cartoonish transformation effect of full-body disguise, where it turns out that another person or a cartoon character has been inside the source person all along (or vice versa) when the first person unzips their skin. This lora is tested to run in kijai's Wan Wrapper nodes + ComfyUI essentials for histogram correction of 0.2 (otherwise the frames will be too dark), with the default lora weight of 1.0. The LoRA has been trained using diffusion-pipe for 70 epoch with variable flow shift: 4.3 (for ~ 40 epochs) -> 3.9 to capture both macroscopic changes (the falling skin) first and then the exact hand movements, using Prodigy optimizer. The train resolutions are 688x688x49 and 688x688x65. As the text encoder is not trained, the keywords have little effect, and I recommend describing the action in details following the prompt-template below: """ The video begins with [object]. [She/He] touches the top of [her/his] head with [her/his] hand and then [she/he] fully unzips [her/his] skin in two halves slowly pulling the zip with [her/his] hand across [her/his] body from the top of [her/his] head, splitting [her/his] face, to the waist to reveal [target object] inside [her/him]. The [target object] then throws away the previous skin. """ The ending sentence variation is "The previous skin then falls down", if you don't want to toss it around. Also, you can have the same pictures at the beginning and the end resulting in an endless loop of unpeeling :) This is an experimental lora and the success rate varies! The model sometimes tries to cheat using a "bag" to put the subject into for later unzipping. For the time being, add "bag, shell, case, hood, zipper, cloth, grainy, dark, movie shot, old movie, jungle, vegetation, plants" to the negative prompt. Obviously, the lora works the best when the subjects share the same or at least a similar background.
Kata pencetus
Disguise drop.
529 muat turun · 48 suka di Civitai
SHA256
CD787B513DBB0137133982972A109A8D0A56F9F9161B54BAF4EDF32AD6364F2A
Ranking badge
Updated Oct 22, 2026
Disguise Drop LTX 2 / Wan2.1 14B FLF2V di ModelTrends.ai: #13 Hottest Ltx2 model
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #13 Hottest Ltx2 LoRA
Not this creator?
Trend populariti Disguise Drop LTX 2 / Wan2.1 14B FLF2V
Skor panas sejak 28 Jan 2026
Skor haba
8,030°
Minggu ini
n/a
Belum dikeluarkan/dipantau
Bulan ini
n/a
Belum dikeluarkan/dipantau
Tahun lalu
n/a
Belum dikeluarkan/dipantau
Disguise Drop LTX 2 / Wan2.1 14B FLF2V: Skor panas sejak 28 Jan 20267,000°7,333°7,666°7,999°8,332°Jan 2026Mar 2026May 2026Jul 2026Sep 2026Oct 20268,030°ModelTrends.ai
7,000°
Lantai
Skala berjalan dari 0° hingga 9,999°. Apa sahaja di bawah 7,000° disimpan untuk model yang belum dilaporkan oleh mana-mana sumber, yang membawa nombor gantian di situ supaya senarai tetap lengkap. 7,000° adalah tempat data yang diukur bermula: model dengan data sebenar tapi hampir tiada muat turun berada di lantai, dan ukuran mengisi darjah di atasnya. Lantai tidak memberitahu apa-apa tentang model; hanya darjah di atasnya yang buat beza antara satu model dengan model lain.
+824°
Muat turun Civitai
529 muat turun versi tepat ini di Civitai. Muat turun adalah bahan paling berat dan dikira pada skala logaritma: sepuluh kali muat turun menambah 300° yang sama, jadi model dengan sejuta muat turun tidak sepuluh ribu kali lebih panas daripada yang seribu. Enam sumber muat turun berkongsi satu terma itu, dibahagi mengikut jumlah mereka.
+254°
Suka
48 suka dan jempol naik di semua sumber. Suka seberat setengah muat turun, pada skala log yang sama.
+11°
Kadar penerimaan
Kira-kira 0 muat turun sehari, diukur antara dua bacaan sumber, tidak pernah dianggarkan dari purata sepanjang hayat. Kelajuan seberat suku istilah muat turun, jadi lonjakan baru kelihatan tanpa membiarkan lonjakan satu hari mengatasi penggunaan bertahun-tahun.
+100°
Boost keluarga
+100° sebab ini LoRA dari keluarga yang laman ini sedang galakkan sekarang. Ia adalah dorongan terhad dalam skor dan disenaraikan di sini dengan terbuka; ia tidak boleh sembunyikan model atau lebih berat daripada perbezaan muat turun seribu kali ganda.
−159°
Umur
−159° sebab berat Ltx2 keluar pada 2025. Setiap model mewarisi umur berat yang dibina padanya: 150° setahun, sehingga 750°, dan ia terus bertambah sehingga itu. Tanpanya, senarai teratas akan jadi checkpoint 2022 dan 2023 berdasarkan muat turun yang ada bertahun untuk terkumpul.
Tunjukkan pecahan terperinci
Setiap nombor di laman ini boleh diperiksa. Skor panas model ini adalah 8,030°, dan ia dibina satu bahan pada satu masa, dengan jumlah terkini selepas setiap langkah: lantai, darjah yang ditambah oleh setiap sumber, bonus untuk jenis model dan apa yang umur beratnya tolak. Warna-warna itu adalah jalur carta di atas. Glosari di akhir menerangkan setiap istilah.
  1. 1
    Mula di lantai.
    Kenapa 7,000° dan bukan sifar: skala dari 0° hingga 9,999°, dan bahagian di bawah 7,000° dikhaskan untuk model yang belum dilaporkan oleh mana-mana sumber, yang membawa nombor gantian supaya senarai tetap lengkap dan tidak pernah mengatasi model dengan data. 7,000° adalah tempat data yang diukur bermula. Model dengan data sebenar tapi hampir tiada muat turun berada di sini; semua yang berikut adalah ukuran, dan ruang di atas lantai ada sepuluh langkah muat turun sepuluh kali ganda pada 300° setiap satu. Lantai sama untuk setiap model, jadi ia tidak tentukan apa-apa; darjah di atasnya yang buat beza.
    7,000°
    jumlah berjalan
  2. 2
    Tambah muat turun.
    529 muat turun setara semuanya, dari Muat turun Civitai. Sepuluh kali muat turun menambah 300° yang sama, jadi saiz penting tapi tidak pernah mengatasi skor.
    +824°
    7,824°
    jumlah berjalan
  3. 3
    Tambah suka.
    48 suka dan jempol, dengan berat separuh muat turun.
    +254°
    8,078°
    jumlah berjalan
  4. 4
    Tambah kadar penerimaan.
    Sekitar 0 muat turun sehari sekarang, diukur antara dua bacaan, dengan berat suku.
    +11°
    8,089°
    jumlah berjalan
  5. 5
    Boost keluarga.
    Dorongan terbuka dan terhad untuk LoRA keluarga yang sedang dipromosikan laman ini sekarang.
    +100°
    8,189°
    jumlah berjalan
  6. 6
    Tanggalkan umur.
    Berat Ltx2 keluar pada 2025: 150° setahun, sehingga 750°, bertambah sehingga itu.
    −159°
    8,030°
    jumlah berjalan
  7. =
    Skor heat.
    Di mana model ini berdiri dalam setiap senarai laman ini. Tiada yang lain mengubahnya.
    8,030°
Glosari: istilah yang digunakan di sini
Skor heat
Satu nombor untuk seberapa banyak model digunakan dan diingini sekarang, dari 0° hingga 9,999°. Setiap senarai di laman ini yang kata paling panas disusun mengikutnya dan tiada yang lain.
Lantai
7,000° yang setiap model dengan data sebenar bermula. Skala dari 0° hingga 9,999°; bahagian bawah lantai untuk pengganti (model tanpa data), supaya model dengan data sentiasa lebih tinggi dari yang tiada. Lantai sama untuk semua dan tidak tentukan apa-apa; darjah di atasnya adalah ukuran.
Setara muat turun
Semua yang skor anggap sebagai muat turun, dijumlahkan: muat turun sendiri, setiap torrent seeder sebagai 1,000, setiap imej AI Horde dan setiap larian di laman generasi sebagai satu.
Skala log
Mengira dengan puluhan, bukan satuan: dari 1,000 ke 10,000 muat turun tambah darjah sama seperti dari 10,000 ke 100,000. Ini elak gergasi menindas yang lain.
Suka
Jempol dan suka dari semua sumber, bernilai separuh muat turun pada skala log.
Kadar penerimaan
Berapa banyak muat turun sehari model dapat sekarang, dari beza dua bacaan sumber. Berat suku dari terma muat turun.
Diukur dan dianggarkan
Diukur bermaksud ada dua bacaan dari satu sumber dan perbezaannya adalah nyata. Dianggarkan bermaksud hanya jumlah hari ini yang diketahui dan masa lalu diagihkan sepanjang hayat model; laman web akan memberitahu yang mana satu ia tunjukkan.
Seeder
Seseorang yang menyimpan salinan berat secara dalam talian untuk dimuat turun oleh orang lain melalui torrent, atau cermin yang dihoskan melakukan perkara yang sama. Setiap satu dikira sebagai 1,000 muat turun.
AI Horde
Rangkaian sukarelawan yang menjana imej secara percuma pada komputer yang didermakan. Bilangan imej yang telah dihasilkan dengan model adalah awam, dan setiap satu dikira sebagai satu muat turun.
Laman penjanaan
Laman yang menghoskan salinan model mereka sendiri dan membenarkan orang menjana dengannya, seperti PixAI, SeaArt dan Yodayo. Muat turun mereka dikira seperti Civitai dan setiap sesi penjanaan dikira sebagai satu muat turun.
Token OpenRouter
Model teks yang disediakan melalui API, seperti Claude atau GPT, tidak mempunyai berat untuk dimuat turun, jadi penggunaannya diukur dalam token: bahagian teks yang dibaca dan ditulis melalui OpenRouter, pintu masuk yang digunakan oleh banyak aplikasi, dalam 30 hari terakhir. Setiap 10,000,000 token dikira sebagai satu muat turun. Sumber: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Model penuh (checkpoint)
Berat itu sendiri, fail yang menjana secara sendiri. Ia mendapat bonus kerana add-on bergantung padanya.
LoRA dan embedding
Fail add-on kecil yang mengarahkan berat orang lain ke arah gaya, watak atau konsep. Ia tidak boleh dijalankan sendiri.
Keluarga dan berat
Asas yang model dibina, seperti SD 1.5, SDXL, Flux atau Wan. Setiap model mewarisi tarikh keluaran berat keluarganya.
Umur
Darjah yang ditolak berdasarkan berapa lama berat keluarga itu dikeluarkan: 150° setahun, sehingga 750°. Ia mengekalkan muat turun lama yang mempunyai masa bertahun-tahun untuk terkumpul dengan membekukan di bahagian atas senarai.
Peningkatan keluarga
Dorongan kecil dan terhad untuk LoRA dari keluarga yang laman ini sedang galakkan sekarang, sentiasa disenaraikan dalam pecahan.
Skor gantian
Nombor stabil di bawah paras yang diberikan kepada model yang belum ada laporan sumber, supaya senarai kekal lengkap. Ia tidak pernah mendahului model yang ada data.
Baru! (tempoh kelonggaran)
Model yang berumur kurang dari 7 hari menunjukkan Baru! dan tidak mempunyai skor serta tidak menduduki tempat dalam kedudukan. Skornya dikira dari hari pertama, tetapi model yang berumur satu hari berkembang lebih cepat daripada apa pun, jadi tanpa menunggu, #1 minggu ini akan sentiasa menjadi apa sahaja yang keluar semalam dan bukan yang bertahan selama seminggu.
Trend
Bagaimana pertumbuhan model dalam tempoh tertentu dibandingkan dengan pertumbuhan model biasa dalam tempoh yang sama. Lebih cepat dari biasa bermaksud naik, lebih perlahan bermaksud turun.
Model biasa
Tengah katalog: separuh model dengan angka tumbuh lebih cepat dalam tempoh itu, separuh lagi lebih perlahan.
Bagaimana populariti model ini bergerak berbanding katalog lain: pertumbuhannya dalam muat turun, suka dan penggunaan setiap tempoh, diukur berbanding pertumbuhan model biasa dalam tempoh yang sama, dengan skor panasnya pada masa itu. Di atas pertumbuhan biasa dibaca sebagai kenaikan, di bawahnya sebagai penurunan. Masa lalu dibina semula dari jumlah hari ini, hari pertama model dan kelajuan muat turun yang diukur jika ada dua bacaan; model yang tidak wujud pada permulaan tempoh menunjukkan n/a.
Contoh render
Prompt dan tetapan yang dikongsi oleh orang yang membuat render ini di Civitai. Pilih render untuk melihat cara ia dibuat.
Contoh render 1
Contoh render 2
Contoh render 3
Contoh render 4
Contoh render 5
Contoh render 6
Contoh render 7
Render NSFW, dikaburkan. Hidupkan NSFW untuk melihatnya.
Contoh render 8
Render NSFW, dikaburkan. Hidupkan NSFW untuk melihatnya.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Seed
42
Saiz
1024x1024
Prompt
The video starts with multiple mice near a crushed cheese. Then suddenly the camera moves and focuses on the anthropomorphic mouse behind all them. The mouse stands on its two legs and, while the camera zooms out, the mouse touches the top of its gray head with its hand and then it fully unzips its skin in two halves slowly pulling the zip with its hand across its body from the top of its head, splitting its face, to the waist to reveal a fierce gigantic colossal ginger cat which roars furiously. The cat slowly increases in size as it is ejected from the mouse's gray skin. The previous unzipped skin falls down. The rest three of the mice run away in horror while the cat starts to chase them. Only one mouse unzips itself, the others keep the mouse form. There is only one skin layer. Dynamic pursuit scene. The cat is aggressive and angry and chases the mice.
Prompt negatif
washed out, gray, blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Seed
36
Saiz
1024x1024
Prompt
Disguise drop. A knight in shining, bulky armor stands in a castle courtyard. He struggles to move, then has an idea. He unzips the chest plate, revealing not a man, but a clever miniature raccoon inside. The miniature raccoon pops out, drops the suit, and scurries off with a piece of stolen treasure.
Prompt negatif
Furry, the fox is furry. The fox is 3D. The chicken on the right unzips her skin, washed out, gray, blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Seed
31
Saiz
1024x1024
Prompt
Disguise drop. The girl touches the top of her head with her hand and then she fully unzips her skin in two halves slowly pulling the zip with her hand across her body from the top of her head, splitting her face, to the waist to reveal a smug anime style anime girl. She throws away the previous unzipped skin.
Prompt negatif
washed out, gray, blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Seed
38
Saiz
1024x1024
Prompt
Disguise drop. The anime girl touches the top of her head with her hand and then she fully unzips her skin in two halves slowly pulling the zip with her hand across her body from the top of her head, splitting her face, to the waist to reveal a realistic man. The man pulls off the skin, moving his legs out of it. He throws away the previous unzipped skin.
Prompt negatif
washed out, gray, blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Seed
132322232569358
Saiz
1024x1024
Prompt
The video starts with two anime girls: the girl on the left has yellow sweater, yellow hair, green eyes and purple trousers and the girl on the right has white shirt, black hair, blue eyes and blue skirt. The girl on the right says: "You are me!". Then the girl on the left decides to change her shape: the girl on the left touches the top of her own head with her hand and then she fully unzips her skin in two halves slowly pulling the zip with her hand across her body from the top of her head, splitting her face, to the waist to reveal a short girl looking just like the initial girl on the right: an anime girl with white shirt, black hair, sky blue eyes and a blue skirt. The previous unzipped skin falls down. The girl on the right looks at her curiously. The girl on the right says: "And I am you!". Now with the same looking two girls standing, a reciprocal situation happens: the girl on the right touches the top of her own head with her hand and then she fully unzips her skin in two halves slowly pulling the zip with her hand across her body from the top of her head, splitting her face, to the waist to reveal a tall girl looking just like the initial girl on the left: an anime girl with yellow sweater, yellow hair, green eyes and blue trousers. The previous unzipped skin falls down.
Prompt negatif
The girls speak at the same time, washed out, gray, blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Seed
32
Saiz
1024x1024
Prompt
Disguise drop. The girl touches the top of her head with her hand and then she fully unzips her skin in two halves slowly pulling the zip with her hand across her body from the top of her head, splitting her face, to the waist to reveal a realistic wolf. The wolf throws away the previous unzipped skin.
Prompt negatif
The girl unzips the skin twice. washed out, gray, blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, unreadable text on shirt or hat, incorrect lettering on cap (“PNTR”), incorrect t-shirt slogan (“JUST DO IT”), missing microphone, misplaced microphone, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, smiling, laughing, exaggerated sadness, wrong gaze direction, eyes looking at camera, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, missing sniff sounds, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, missing door or shelves, missing shallow depth of field, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.
Tetapan
Sampler
Euler
Langkah
20
Guidance
4
Saiz
944x1280
Prompt
The girl reaches up and grabs something on the back of her scalp with her hand and then she fully unzips her skin in two halves slowly pulling the zip with her hand across her body from the top of her head performing a Disguise drop, splitting her face, to the waist to reveal a laughing smaller girl of the same style but with smaller breasts, brown/black hair, The bodysuit she was wearing drops down to the floor, throwing away the previous unzipped skin, she then looks at the camera, puts her hands on her hips and giggles mischievously with her eyes closed.
Tetapan
Saiz
1080x1350
Prompt
Note Disguise drop Lora causes picture to get washed out, I had to use post processing to correct color LTXNUDES, Polar bear sitting by a camp fire, A british female voiceover confidently says "We're full of surprises."TThe Polar bear stands and unzips the top of its head and pulls off it's disguise. The work "Alaska" displays on top of the video. As the camera pans up sligthly, the disguise falls into the snow to reveal a nude woman standing, while the same british female voiceover says confidently, "Alaska". The woman stands there smiling with the word "Alaska" over her for the last 2 seconds of the video.
Jalankan secara tempatan
ltx2-disguise-drop.safetensors
792 MB · SafeTensor
Muat turun disediakan oleh Civitai. Sesetengah pencipta memerlukan log masuk Civitai dahulu.