Automatické přehrávání
Spustit lokálně
kxsr_WAN1-3B_fpv_flying_concept.safetensors
167 MB · SafeTensor
Stahování zajišťuje Civitai. Někteří autoři vyžadují nejprve přihlášení na Civitai.
AD
Instalovat / Spustit na Graydient
Vyžaduje členství
<flying-firstperson-wan>
O tomto modelu
WAN · LoRA
by Kytra - Example Prompts kxsr, a person flying in first-person perspective through a raging forest fire, the camera descends through burning trees with smoke and ash rising into the sky
Poznámky autora
KXSR First-Person Flight Concept LorA for WAN 2.1 14B and 1.3B T2V
In collaboration with [ Labs presents:
This LoRA enables the creation of cinematic first-person perspective flying. The hands can be customized in the prompt provided or omitted from the prompt for raw forward camera movement. The typical view will be from a first-person perspective with dynamic movement in horizontal aspect ratio generation. Can still create fun results at other aspect ratios/resolutions.
Use the trigger word "kxsr" to activate the model's specialized training.
Prompt Format
kxsr, [flying in first-person perspective/a person flying in first-person perspective] [broad description of landscape] [describe visible body parts (hands/fists)] [describe movement direction and speed] [describe additional environmental details encountered during flight]
Example Prompts
kxsr, a person flying in first-person perspective through a raging forest fire, the camera descends through burning trees with smoke and ash rising into the sky
=================================================
kxsr, a person flying in first-person perspective through an underwater atlantis city, mermaid hands with painted fingernails visible, the camera descends into bubbling water and zooms through the sunken ornate ruins
Recommended Settings
-
CFG: 4
-
Shift value: 4.0
-
LoRA strength: 1.0
-
~73 frames
-
720x1280 horizontal aspect ratio
Technical Details
-
Base model: WAN 2.1 14B and 1.3B Text2Video
-
Training dataset: 62 clips
-
Resolution: 1280 x 720 (horizontal format)
-
Frame count: 73 frames per clip
-
For optimal results, maintain these specifications during inference
This LoRA works best when you provide detailed descriptions of both the subject and the surrounding environment while following the prescribed format.
Screenshot shows my typical inference testing setup for lora evals:
Spouštěcí slova
kxsr
SHA256
627E2DE8AB804C1DF0D911FE6EEC05CCDEB46555A2DE9949A266CC8BFE394031
ID modelu ModelTrends.ai
#11558
Nahlásit obsah
Ukázkové rendery
Prompty a nastavení sdílená lidmi, kteří tyto rendery vytvořili na Civitai. Vyberte render a uvidíte, jak vznikl.
Nastavení
Velikost
1280x720
Prompt
kxsr, first person view, a mermaid swims, parting the water with both hands, from a first person view through the underwater city of Atlantis, the mermaid's hands are visible, covered in scales, with painted nails, the camera descends into the seething water and moves through the sunken richly decorated ruins.
Nastavení
Kroky
50
Guidance
4
Velikost
1280x720
Prompt
kxsr, a person flying in first-person perspective above an elven city with ornate fantasy building, the camera descends into the marble streets, nightelf hands with painted fingernails visible
Nastavení
Velikost
640x480
Prompt
kxsr, a person flying in first-person perspective above toronto skyline, pass by cn tower, the camera descends into the city streets, hands visible
Podobné modely
AI modely pro generování obrázků, videa a textu
flying firstperson wan je LoRA pro rodinu Wan uvedený na ModelTrends.ai, katalogu open source AI modelů pro obrázky, video a text určeném jen ke čtení. Porovnejte ho s dalšími modely Wan, podívejte se na jeho skóre žhavosti a vyzkoušejte ho na PirateDiffusion nebo BitVector.
Procházet podle rodiny modelů
Modely Text / LLM
411
Modely Anima
509
Modely Chroma
14
Modely Flux
1,071
Modely Flux 2 / Klein
1,237
Modely MiniMax H3
331
Modely Hunyuan
197
Modely Ideogram
20
Modely Krea2
674
Modely Qwen
17
Modely Qwen2
36
Modely Ltx2
150
Modely Stable Diffusion 1.5
6,465
Modely Stable Diffusion XL 1.0
15,432
Modely Zimage
804
Modely Wan
919

Model
Trends
.ai
© ModelTrends.ai
|
Vyrobeno v Japonsku
|
© 2026
