Model
.ai
memantau model AI terbuka

Disguise Drop LTX 2 / Wan2.1 14B FLF2V

8030°
Disguise Drop   LTX 2 / Wan2.1 14B FLF2V
Dibuat oleh
kabachuha
di Civitai
by kabachuha - Disguise Drop - LTX-2 / Wan2.1 14B FLF2V
Catatan pembuat
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 pemicu
Disguise drop.
529 unduhan · 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?
Tren popularitas Disguise Drop LTX 2 / Wan2.1 14B FLF2V
Skor panas sejak 28 Jan 2026
Skor panas
8,030°
Minggu ini
n/a
Belum dirilis/dilacak
Bulan ini
n/a
Belum dirilis/dilacak
Tahun lalu
n/a
Belum dirilis/dilacak
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°
Floor
Skala berjalan dari 0° sampai 9.999°. Semua yang di bawah 7,000° disimpan untuk model yang belum dilaporkan oleh sumber mana pun, yang memakai angka pengganti di sana supaya daftar tetap lengkap. 7,000° adalah titik awal data yang diukur: model dengan data nyata tapi hampir tidak ada unduhan berada di floor, dan pengukuran mengisi derajat di atasnya. Floor tidak mengatakan apa-apa tentang model; hanya derajat di atasnya yang berbicara, dan itu yang membedakan satu model dengan yang lain.
+824°
Unduhan Civitai
529 unduhan versi tepat ini di Civitai. Unduhan adalah bahan terberat dan dihitung dalam skala log: sepuluh kali unduhan menambah 300° yang sama, jadi model dengan sejuta unduhan tidak seribu kali lebih panas dari yang seribu unduhan. Enam sumber unduhan berbagi satu istilah itu, dibagi proporsional sesuai jumlahnya.
+254°
Suka
48 suka dan jempol ke atas dari berbagai sumber. Suka dihitung setengah unduhan, dengan skala log yang sama.
+11°
Tingkat adopsi
Sekitar 0 unduhan per hari, diukur antara dua pembacaan sumber, tidak pernah ditebak dari rata-rata seumur hidup. Kecepatan dihitung seperempat dari istilah unduhan, jadi lonjakan baru terlihat tanpa membiarkan lonjakan satu hari mengalahkan penggunaan bertahun-tahun.
+100°
Bonus keluarga
+100° karena ini LoRA dari keluarga yang sedang didorong situs ini sekarang. Ini dorongan terbatas dalam skor dan tercantum di sini secara terbuka; tidak pernah bisa menyembunyikan model atau mengalahkan perbedaan unduhan seribu kali lipat.
−159°
Usia
−159° karena bobot Ltx2 keluar di 2025. Setiap model mewarisi usia bobot yang dipakai: 150° per tahun, sampai 750°, dan terus bertambah sampai itu. Tanpa ini, puncak daftar akan diisi checkpoint 2022 dan 2023 hanya karena unduhan yang sudah bertahun-tahun menumpuk.
Tampilkan rincian
Setiap angka di situs ini bisa dicek. Skor heat model ini adalah 8,030°, dan ini dibangun satu bahan pada satu waktu, dengan total berjalan setelah setiap langkah: floor, derajat yang ditambahkan setiap sumber, bonus untuk jenis model dan pengurangan karena usia bobotnya. Warna-warna itu adalah rentang pada grafik di atas. Glosarium di akhir menjelaskan setiap istilah.
  1. 1
    Mulai dari floor.
    Kenapa 7,000° dan bukan nol: skala dari 0° sampai 9.999°, dan bagian di bawah 7,000° disediakan untuk model yang belum dilaporkan sumber mana pun, yang memakai angka pengganti supaya daftar tetap lengkap dan tidak pernah mengalahkan model dengan data. 7,000° adalah titik awal data yang diukur. Model dengan data nyata tapi hampir tidak ada unduhan berada di sini; semua yang berikutnya adalah pengukuran, dan ruang di atas floor memuat sepuluh langkah sepuluh kali lipat unduhan dengan 300° masing-masing. Floor sama untuk semua model, jadi tidak menentukan apa-apa; yang menentukan adalah derajat di atasnya.
    7,000°
    total berjalan
  2. 2
    Tambahkan unduhan.
    529 setara unduhan secara total, dari Unduhan Civitai. Sepuluh kali unduhan menambah 300° yang sama, jadi ukuran penting tapi tidak pernah mendominasi skor.
    +824°
    7,824°
    total berjalan
  3. 3
    Tambahkan suka.
    48 suka dan jempol ke atas, dengan bobot setengah dari satu unduhan.
    +254°
    8,078°
    total berjalan
  4. 4
    Tambahkan tingkat adopsi.
    Sekitar 0 unduhan per hari sekarang, diukur antara dua pembacaan, dengan bobot seperempat.
    +11°
    8,089°
    total berjalan
  5. 5
    Dorongan keluarga.
    Dorongan terbuka dan terbatas untuk LoRA dari keluarga yang sedang didorong situs ini sekarang.
    +100°
    8,189°
    total berjalan
  6. 6
    Lepaskan usia.
    Bobot Ltx2 keluar di 2025: 150° per tahun, sampai 750°, bertambah sampai saat itu.
    −159°
    8,030°
    total berjalan
  7. =
    Skor heat.
    Posisi model ini di setiap daftar di situs ini. Tidak ada yang mengubahnya selain ini.
    8,030°
Glosarium: istilah yang dipakai di sini
Skor heat
Satu angka untuk seberapa banyak model dipakai dan diinginkan sekarang, dari 0° sampai 9.999°. Setiap daftar di situs ini yang bilang terpanas diurutkan berdasarkan ini dan tidak ada yang lain.
Lantai
7.000° yang jadi titik awal semua model dengan data nyata. Skala dari 0° sampai 9.999°; bagian di bawah lantai untuk pengganti (model tanpa data), supaya model dengan data selalu di atas yang tanpa. Lantai sama untuk semua dan tidak menentukan apa-apa; derajat di atasnya yang dihitung.
Setara unduhan
Semua yang dihitung skor sebagai unduhan, dijumlahkan: unduhan itu sendiri, setiap torrent seeder dihitung 1.000, setiap gambar AI Horde dan setiap run di situs generasi dihitung satu.
Skala log
Menghitung per puluhan, bukan per satuan: naik dari 1.000 ke 10.000 unduhan menambah derajat yang sama dengan naik dari 10.000 ke 100.000. Ini mencegah raksasa mendominasi semuanya.
Suka
Jempol ke atas dan suka dari semua sumber, bernilai setengah unduhan di skala log.
Tingkat adopsi
Berapa banyak unduhan per hari yang didapat model sekarang, dari selisih dua pembacaan sumber. Bobot seperempat dari istilah unduhan.
Diukur dan diperkirakan
Diukur berarti ada dua pembacaan dari sumber dan perbedaannya nyata. Diperkirakan berarti hanya total hari ini yang diketahui dan masa lalu dibagi selama umur model; situs memberitahu mana yang sedang ditampilkan.
Seeder
Seseorang yang menyimpan salinan bobot secara online agar orang lain bisa mengunduh lewat torrent, atau mirror yang dihosting melakukan hal yang sama. Setiap satu dihitung sebagai 1.000 unduhan.
AI Horde
Jaringan sukarelawan yang menghasilkan gambar secara gratis di komputer yang disumbangkan. Jumlah gambar yang dibuat dengan model tertentu bersifat publik, dan setiap gambar dihitung sebagai satu unduhan.
Situs generasi
Situs yang menyimpan salinan model sendiri dan membiarkan orang menghasilkan gambar dengannya, seperti PixAI, SeaArt, dan Yodayo. Unduhan mereka dihitung seperti di Civitai dan setiap kali generasi dihitung sebagai satu unduhan.
Token OpenRouter
Model teks yang dilayani melalui API, seperti Claude atau GPT, tidak memiliki bobot untuk diunduh, jadi penggunaannya diukur dalam token: potongan teks yang dibaca dan ditulis melalui OpenRouter, gateway yang digunakan banyak aplikasi, selama 30 hari terakhir. Setiap 10,000,000 token dihitung sebagai satu unduhan. Sumber: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Model penuh (checkpoint)
Bobot itu sendiri, file yang bisa menghasilkan secara mandiri. Mendapat bonus karena add-on bergantung padanya.
LoRA dan embedding
File add-on kecil yang mengarahkan bobot orang lain ke gaya, karakter, atau konsep tertentu. Tidak bisa dijalankan sendiri.
Keluarga dan bobot
Dasar yang dipakai model, seperti SD 1.5, SDXL, Flux, atau Wan. Setiap model mewarisi tanggal rilis bobot keluarganya.
Usia
Pengurangan nilai berdasarkan seberapa lama bobot keluarga itu dirilis: 150° per tahun, sampai maksimal 750°. Ini menjaga unduhan lama yang sudah bertahun-tahun menumpuk agar tetap di atas daftar.
Dorongan keluarga
Dorongan kecil dan terbatas untuk LoRA dari keluarga yang sedang didorong situs ini sekarang, selalu tercantum dalam rincian.
Skor pengganti
Angka stabil di bawah batas yang diberikan pada model yang belum ada laporan sumbernya, supaya daftar tetap lengkap. Tidak pernah lebih tinggi dari model yang punya data.
Baru! (masa tenggang)
Model yang berumur kurang dari 7 hari menunjukkan label Baru! bukan skor dan tidak masuk peringkat. Skornya dihitung sejak hari pertama, tapi model yang baru sehari tumbuh lebih cepat dari apa pun, jadi tanpa masa tunggu model #1 minggu ini selalu yang baru kemarin, bukan yang bertahan seminggu.
Tren
Bagaimana pertumbuhan model selama periode tertentu dibandingkan dengan pertumbuhan model biasa di periode yang sama. Lebih cepat dari biasanya berarti naik, lebih lambat berarti turun.
Model biasa
Tengah katalog: setengah model dengan angka tumbuh lebih cepat selama periode itu, setengahnya lebih lambat.
Bagaimana popularitas model ini bergerak dibandingkan dengan katalog lainnya: pertumbuhan unduhan, suka, dan penggunaan setiap periode, diukur terhadap pertumbuhan model biasa dalam periode yang sama, dengan skor panasnya saat itu. Di atas pertumbuhan biasa berarti naik, di bawahnya berarti turun. Masa lalu direkonstruksi dari total hari ini, hari pertama model, dan kecepatan unduhan yang diukur jika ada dua pembacaan; model yang belum ada di awal periode menunjukkan n/a.
Contoh render
Prompt dan pengaturan yang dibagikan oleh orang-orang yang membuat render ini di Civitai. Pilih sebuah render untuk melihat cara membuatnya.
Contoh render 1
Contoh render 2
Contoh render 3
Contoh render 4
Contoh render 5
Contoh render 6
Contoh render 7
Gambar NSFW, diburamkan. Nyalakan NSFW untuk melihatnya.
Contoh render 8
Gambar NSFW, diburamkan. Nyalakan NSFW untuk melihatnya.
Render by kabachuha on
Civitai
·
Prompt on BunchaPrompts
Laporkan
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Seed
42
Ukuran
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
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Seed
36
Ukuran
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
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Seed
31
Ukuran
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
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Seed
38
Ukuran
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
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Seed
132322232569358
Ukuran
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
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Seed
32
Ukuran
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.
Pengaturan
Sampler
Euler
Langkah
20
Guidance
4
Ukuran
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.
Pengaturan
Ukuran
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 lokal
ltx2-disguise-drop.safetensors
792 MB · SafeTensor
Unduhan disediakan oleh Civitai. Beberapa kreator meminta login Civitai terlebih dahulu.