Model
Trends
.ai
Model
Trends
.ai
model AI sumber terbuka terbaik
Jalankan secara tempatan
Lenovo.safetensors
293 MB · SafeTensor
Muat turun disediakan oleh Civitai. Sesetengah pencipta memerlukan log masuk Civitai dahulu.
AD
<ultrareal-wan>
Tentang model ini
WAN · LoRA
Dicipta oleh
Danrisi
di Civitai
By:Danrisi This is the first release — mainly a test to explore Wan's capabilities. Note: In this initial version, facial details are somewhat lacking. For better results, I recommend using it alongside the Instagirls LoRA by my friend, which significantly enhances facial features. Trigger word: l3n0v0
Nota pencipta
--Qwen2.1 Me recommendations: 3-4 cfg (but if image become slop, then change to 1) beta scheduler, res_2m / res_2s / res_multistep (2s best quality, multistep the fastest, 2m balance) I'll post my flow a bit later when finish uploading other loras P.S: im in a hurry so more exmaples will be soon for all my loras --Krea2 Actually i tested with different combinations raw and turbo. For best quality i use raw with cfg4, for fast result i use raw, but witth cfg1 and turbo lora (it really gives better quality then kreo2 turbo model). U can use with other loras freely, also works good with nicegirls lora and nsfw loras. recommended weight 0.8 for raw and 1.2-2 for turbo --Ideogram4 Works good with for nsfw images. Also updated my repo for better lora control One more. Made cool nodes with cursor (i have no clue how some of them to use) for ideogram --Anima1.0 Trained on top of my last ultrareal_finetune_base1 checkpoint for a slight realism boost. I also "vibecoded" a few experimental nodes for Anima (pretty sure something similar already exists, but here we are): Consider this a temporary realism upgrade until I train the next major fine-tune. --Anima0.5 Trained on anima3. Recommended strength: 0.6. Works best with block filtering — I created a ComfyUI nodepack for this: . Examples generated alongside my other LoRA — nicegirls. Experimental version. Results may vary depending on prompt and block weight settings. --Flux2 I use it with res2m+beta57, guidance 4, and it works very well. The quality is similar to my Qwen Lenovo, but I noticed that Flux2 is more flexible and has better prompt adherence. Recommend to use with strength 0.85-0.9 -- Z-image Turbo Actually i'm not sure that my workflow is correct, i believe the result could be better Recommend to use with strength 0.80-0.9 I used euler + sgm_uniform with 4 guidance P.S: at this moment for ComfyUI u need this pack to load lora properly --Chroma My first try to train lora that enhance realism in Chroma. I'll upload my workflow today a lil bit later (or atm u can just take it from images) cause there some nuances about settings. But from my observations i noticed that for fast gen dpmpp2m + beta with cfg 3 works good . More experimental settigns are res_2s_rkmk2e + beta57 and cfg 3, more accurate gens, better limbs and fingers, but gives a bit weird grain on very small details + plus this method is pretty long --Qwen Works perfectly and much better then other versions. Gives extremely "live" images with amateurish quality with dramatic light and shadows, some blur and with vibe of 2000s street photography You can take workflow here Thanx to . i understood that it's possible (and even have better effect) to use lora with values 1.5 - 2.0. P.S.: almost all example images generate with both loras (NiceGirls) --Wan This is the first release — mainly a test to explore Wan's capabilities. Note: In this initial version, facial details are somewhat lacking. For better results, I recommend using it alongside the by my friend, which significantly enhances facial features. --Flux Who needs a fancy name when the shadows and highlights do all the talking? This experimental LoRA is the scrappy cousin of my Samsung one—same punchy light-and-shadow mojo, but trained on a chaotic mix of pics from my ancient phones (so no Samsung for now)
Kata pencetus
l3n0v0
20,808 muat turun · 686 suka di Civitai
SHA256
64002D78EDC3CEA47D440C4D7BD7BB9DE9C8A67177FE10607632CD6281144631
ID Model ModelTrends.ai
#22914
Laporkan kandungan
Contoh render
Prompt dan tetapan yang dikongsi oleh orang yang membuat render ini di Civitai. Pilih render untuk melihat cara ia dibuat.
Tetapan
Sampler
res_2m
Langkah
30
Guidance
3
Seed
945891564695855
Saiz
1024x1536
Prompt
l3n0v0, Instagirl. underexposed outdoor scene, young caucasian woman with fair skin, oval face, she is Kim from Kim Possible, adorable, athletic slim build, flowing fiery red hair with a side-swept bang, vivid green eyes, black cropped turtleneck top, olive‑green cargo pants, brown utility belt with metallic buckle and compact gadgets, fingerless gloves, she standing at a gas station at night. She is leaning on a heavily tuned purple 2005 Cadillac Deville with a custom body kit. Kim is looking directly at the camera with dreamy expression, holding a white plastic cup with a purple drink. One of her hands, resting on the car, Fisheye lens effect. amateurish quality, candid style
Prompt negatif
8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Tetapan
Sampler
res_2m
Langkah
30
Guidance
3
Seed
1056817938618788
Saiz
1088x1472
Prompt
l3n0v0. underexposed outdoor scene, teenager girl, casual style, wearing dark trench coat, long wavy brown hair cascading over her shoulders, looking direct at the viewer, gothic heavy makeup, outdoors in the dark forest, autumn, smoking cigarette with smoke, showing middle finger not point finger, sunlight filtering through the trees. amateur quality, low resolution, candid style
Prompt negatif
8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Tetapan
Sampler
Euler
Langkah
4
Guidance
1
Seed
792575940803755
Saiz
480x832
Prompt
A lively, photorealistic selfie-style video of a young Asian woman walking alone down a subway platform in the early afternoon. She’s recording herself with her iPhone, holding the camera close in vertical orientation. The footage feels casual and authentic, with natural shakiness and subtle stabilization as she moves. She has a soft oval face, large expressive eyes, thick lips, and slightly tousled hair that shifts gently with her motion. She wears a fitted crop top and loose, baggy jeans, with white AirPods in her ears and a casual handbag slung over one shoulder. While walking forward, she casually glances around, subtly checking her surroundings with curiosity and awareness. Suddenly, she lifts her hand to flash a playful finger peace sign toward the camera and winks with one eye, her lips forming a slight smirk. The lighting is natural and urban—soft shadows from overhead fluorescent lights cast across the platform. There's a shallow depth of field, with the background subtly blurred to emphasize her presence. Reflections from nearby subway surfaces flicker as she moves, and the camera picks up smooth auto-exposure shifts and brief lens refocusing, just like a real phone video. The vibe is upbeat, candid, and charismatic—like a TikTok story filmed on the go.
Prompt negatif
A lively, photorealistic selfie-style video of a young Asian woman walking alone down a subway platform in the early afternoon. She’s recording herself with her iPhone, holding the camera close in vertical orientation. The footage feels casual and authentic, with natural shakiness and subtle stabilization as she moves. She has a soft oval face, large expressive eyes, thick lips, and slightly tousled hair that shifts gently with her motion. She wears a fitted crop top and loose, baggy jeans, with white AirPods in her ears and a casual handbag slung over one shoulder. While walking forward, she casually glances around, subtly checking her surroundings with curiosity and awareness. Suddenly, she lifts her hand to flash a playful finger peace sign toward the camera and winks with one eye, her lips forming a slight smirk. The lighting is natural and urban—soft shadows from overhead fluorescent lights cast across the platform. There's a shallow depth of field, with the background subtly blurred to emphasize her presence. Reflections from nearby subway surfaces flicker as she moves, and the camera picks up smooth auto-exposure shifts and brief lens refocusing, just like a real phone video. The vibe is upbeat, candid, and charismatic—like a TikTok story filmed on the go.
Tetapan
Sampler
res_2m
Langkah
30
Guidance
3
Seed
370083881010519
Saiz
1472x1088
Prompt
l3n0v0. underexposed outdoor scene, young slavic woman, early 20s, looking at the viewer, dreamy expression, gaze directed to the bottom, fair-skinned, wet hair clinging to face, long straight blonde hair, wearing black wet dress with ruffled collar, standing amidst lush greenery, vibrant red flowers surrounding, heavy rain falling, outdoor garden setting, overcast lighting, raindrops visible in mid-air, close-up angle, natural lighting conditions. amateur quality, candid style
Prompt negatif
8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Tetapan
Sampler
Euler
Langkah
4
Guidance
1
Seed
59741186139574
Saiz
480x832
Prompt
(A lively, photorealistic selfie-style video of a young Asian woman walking alone down a bustling subway platform in the early afternoon. She’s casually recording herself with her iPhone in vertical orientation, the footage slightly shaky but smoothly stabilized—authentic phone camera energy. She has a soft oval-shaped face, large expressive eyes, thick lips, and slightly tousled dark hair. She wears a pulled crop top. She glances around with relaxed curiosity, casually checking out her surroundings. Her lips forming a flirty kissy face, confident smirk. She on top of a man getting fucked in the pussy in the cowboy sex position. The station is alive with energy—commuters walk past in the background, some standing near pillars, others waiting by the edge. A train passes behind her on a nearby track, its motion slightly blurred for realism, creating dynamic depth and urban motion. Overhead fluorescent lights cast soft shadows, and ambient platform lighting reflects off tiled walls and the moving train. The background has a gentle depth of field blur, while her face remains sharp and expressive, enhanced by natural lighting and slight camera focus shifts. The atmosphere is energetic, casual, and unmistakably real—like a spontaneous clip shared on social media.:2.0)
Prompt negatif
A lively, photorealistic selfie-style video of a young Asian woman walking alone down a subway platform in the early afternoon. She’s recording herself with her iPhone, holding the camera close in vertical orientation. The footage feels casual and authentic, with natural shakiness and subtle stabilization as she moves. She has a soft oval face, large expressive eyes, thick lips, and slightly tousled hair that shifts gently with her motion. She wears a fitted crop top and loose, baggy jeans, with white AirPods in her ears and a casual handbag slung over one shoulder. While walking forward, she casually glances around, subtly checking her surroundings with curiosity and awareness. Suddenly, she lifts her hand to flash a playful finger peace sign toward the camera and winks with one eye, her lips forming a slight smirk. The lighting is natural and urban—soft shadows from overhead fluorescent lights cast across the platform. There's a shallow depth of field, with the background subtly blurred to emphasize her presence. Reflections from nearby subway surfaces flicker as she moves, and the camera picks up smooth auto-exposure shifts and brief lens refocusing, just like a real phone video. The vibe is upbeat, candid, and charismatic—like a TikTok story filmed on the go.
Tetapan
Sampler
res_2m
Langkah
30
Guidance
3
Seed
676680164189064
Saiz
1088x1472
Prompt
l3n0v0, Instagirl. underexposed indoor scene, young caucasian woman with fair skin, oval face, wear black pvc leggings and a white shirt lying face down on a bed face down, jet black messy bobcut hair, pale skin, barefoot, wrinkled soles. The angle is awkward. A dark room. The photo shows the bed from above. A small lamp backlight illuminates the scene. dim light, she is looking back at the viewer. amateurish unedited raw iphone photo
Prompt negatif
8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Tetapan
Sampler
res_2m
Langkah
30
Guidance
3
Seed
1080953614816975
Saiz
1088x1472
Prompt
l3n0v0, Instagirl. erexposed indoor scene, beautiful young woman with high cheekbones and a highly fashionable gothic outfit. sitting on a black gothic throne inside a gothic temple with muted light. She is holding a knight sword. she wears gothic jewellery. Stained Glass windows. slightly parted lips, extremely long black nails, light smirk expression. tight leather corset with straps with buckles. amateur quality, low resolution, candid style, amateur cellphone quality visible sensor noise, artificial over-sharpening, heavy HDR glow, amateur photo, blown-out highlights, crushed shadows
Prompt negatif
8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Tetapan
Sampler
res_2m
Langkah
30
Guidance
3
Seed
289841936435516
Saiz
1472x1088
Prompt
l3n0v0, Instagirl. underexposed indoor scene, Dimly lit kitchen, late afternoon light casting warm shadows, countertop with stainless steel sink to the left, beside a clean modern gas stove, a red pot with a black handle rests on the burner, creamy tiled backsplash with a tan diamond pattern, horizontal window blinds partially drawn, through which an intense red and orange sunset silhouettes tree branches, the room is predominantly in shadow, with sunlight reflecting subtly off surfaces, strong contrast; teenager girl standing in extravagant pose, vear crop top and skirt. amateur quality, candid style
Prompt negatif
8k, UHD, hyper-realism, cinematic, glossy finish, shallow depth of field, cinematic bokeh, plastic skin, uncanny anatomy, frame-perfect symmetry, blurred background, fat, old, milf, big lips, asian
Model AI untuk penjanaan imej, video dan teks
ultrareal wan ialah LoRA untuk keluarga Wan yang disenaraikan di ModelTrends.ai, katalog baca sahaja untuk model AI imej, video dan teks sumber terbuka. Bandingkannya dengan model Wan lain, semak skor habanya untuk melihat trendnya, dan bukanya di PirateDiffusion atau BitVector untuk mencubanya.
Layari mengikut keluarga model
Layari semua model