How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Danrisi/UltraReal_FineTune_Anima_base1", dtype=torch.bfloat16, device_map="cuda")

prompt = "@dslr_photo @professional_photo @posed_photo @available_light A low-angle, full-body portrait of a tall, slender young woman with a petite frame and small breasts, cosplaying D.Va from Overwatch. She is wearing her iconic blue and pink skin-tight bodysuit, with pink triangular makeup markings painted on her cheeks. She is sitting on top of a wooden school desk inside a classroom, looking directly down at the viewer. She is completely barefoot, holding her feet up close to the camera to prominently display her bare soles from a sharp bottom-view perspective. The background shows a softly blurred classroom setting with windows and ambient indoor daylight. The image features a shallow depth of field, sharp focus on the textures of her skin and outfit, and clean professional DSLR rendering. @2010 score_8, score_9"
image = pipe(prompt).images[0]

UltraReal_FineTune_Anima_base1

To be completely honest, I trained this model on this specific caption format while I was pretty drunk, so it is what it is lol. I'm not even entirely sure how it works under the hood, and I didn't have enough time to thoroughly test everything out. Also, please don't come at me calling me retarded or saying "it doesn't work like that" - just chill, I'm just experimenting here. Hopefully, you guys can help me with that and test.

Anyway, here is a mini-guide on how it's supposed to work (written by Gemini):

To achieve maximum realism, analog grit, or authentic casual smartphone aesthetics, you should follow the exact prompt structure the model was trained on.

๐Ÿ“ The Prompt Formula:

[Prefix Tags] + [Natural Language Description] + [Suffix Tags & Score]

Prefix Tags (The Setup): Set the camera type, lighting, safety, and shot style at the very beginning.

Core Description (The Scene): Describe the subject, clothing, pose, and background using natural English sentences (avoid messy tag-soup).

Suffix Tags (The Quality & Era): Close your prompt with the simulated year of the photo and the quality score.

๐Ÿ“‹ KEYWORDS TO COPY-PASTE

  1. Camera & Tech Prefixes:

@smartphone_photo โ€” Casual, modern mobile look with subtle computational processing.

@compact_digital_photo โ€” Early 2000s "point-and-shoot" digicam vibe.

@film_photo โ€” Authentic analog look with rich organic textures and grain.

@vhs_screencap โ€” Retro video tape style with scanlines.

@dslr_photo โ€” Clean, professional camera rendering.

  1. Lighting & Style Prefixes:

@available_light โ€” Soft, natural indoor/outdoor daylight.

@direct_flash โ€” Harsh, flat flash (perfect for late-night party vibes or digicam looks).

@candid_photo โ€” Caught-on-camera, unposed, natural moments.

@posed_photo โ€” Deliberate posing.

@mirror_reflection โ€” Perfect for mirror selfies.

@underexposed / @overexposed โ€” For dramatic low-light or high-contrast shots.

  1. Safety Blocks:

@sfw or @nsfw (choose depending on your target generation)

  1. Era & Quality Suffixes (Put at the very end!):

Years: @1995, @2000, @2005, @2010, @2020, @2025

Scores: score_5, score_6, score_7, score_8, score_9 (can be used in negative)

๐Ÿ’ก Tip: Use score_8 or score_9 for high definition and clean details. Use score_6 or score_7 combined with @smartphone_photo or @compact_digital_photo if you want a grittier, intentionally imperfect lo-fi look!

๐Ÿ“ธ EXAMPLE PROMPTS

Modern Smartphone Selfie:

@smartphone_photo @sfw @amateur_photo @candid_photo @available_light A close-up portrait selfie of a 20-year-old woman with neon green hair and heavy eyeliner. She is looking at the camera with a neutral expression. The background is a blurry minimalist bedroom. @2025 score_8

Retro Digicam Flash (Vibe from 2005):

@compact_digital_photo @sfw @amateur_photo @posed_photo @direct_flash An overexposed snapshot of a young woman posing in a cluttered room at night. Harsh flash lighting, red-eye effect, visible digital noise, and washed-out colors. @2005 score_7

Analog Film Portrait (Cosplay):

@film_photo @sfw @amateur_photo @candid_photo @available_light A medium shot of a young woman cosplaying Princess Zelda, sitting inside a car. @2015 score_8

P.S.: still WIP, i plan extend dataset and train more

Sample Images

@dslr_photo @professional_photo @posed_photo @available_light A low-angle, full-body portrait of a tall, slender young woman with a petite frame and small breasts, cosplaying D.Va from Overwatch. She is wearing her iconic blue and pink skin-tight bodysuit, with pink triangular makeup markings painted on her cheeks. She is sitting on top of a wooden school desk inside a classroom, looking directly down at the viewer. She is completely barefoot, holding her feet up close to the camera to prominently display her bare soles from a sharp bottom-view perspective. The background shows a softly blurred classroom setting with windows and ambient indoor daylight. The image features a shallow depth of field, sharp focus on the textures of her skin and outfit, and clean professional DSLR rendering. @2010 score_8, score_9

sample

@film_photo @amateur_photo @candid_photo @underexposed. A medium shot of a eastern european young woman with a pale complexion and long blonde hair, cosplaying Princess Zelda from Breath of the Wild, sitting in the indoor cafe. She is wearing her royal blue tunic with elegant white and gold embroidered patterns on the chest, looking at the viewer, head slightly tilted to the side, somber expression, holding cup of coffee. from side view angle. analog film, featuring heavy film grain, a slightly soft vintage focus. dramatic light filtering through the windows, illuminating table and part of her face, hard shadows. The background shows the naturally blurred details of the cafe and people around. @1995 score_8, score_7

sample

@dslr_photo @sfw @posed_photo @experimental_photo @long_exposure @visible_light_trails A 20-year-old East Asian-looking woman posing in a dark tunnel environment, captured with a long-exposure technique that creates distinct, wavy light trails in the background. she cosplaying asuka langley from evangelion, wearing thin-rimmed oval glasses and her red outfit. She has a neutral expression with one eye slightly squinted or winking, point a pistol at the viewer. The lighting is dominated by the deliberate motion-blurred streaks of white and red light that snake around her figure, set against a deep, crushed-black background. The camera work is intentional and artistic, emphasizing the contrast between her steady, sharp face and the swirling energy of the light trails. The overall aesthetic is moody and creative, typical of urban night photography. @2005 score_8, score_7

sample

@compact_digital_photo @sfw @amateur_photo @posed_photo @available_light, candid photo, and dim, natural lighting, set in an outdoor park-like environment, girl that looks like aerith gainsborough from final fantasy, she wear her clothes, sitting on a concrete curb in the foreground, with a dirt ground and the base of a tree in the background, she is sitting hunched forward, hugging her arms to her body with her hands clasped, wearing a somber expression, and gazing downwards and to her left. @2005 score_6, score_7

sample

@dslr_photo @sfw @professional_photo @candid_photo @available_light @mild_bokeh A high-resolution, medium-shot concert photograph of a teen girl that cosplay Hatsune Miku, performing vocals at a black metal concert on a dimly lit stage. She has long turquoise twin-tails tied with black ribbons, pale stage makeup with subtle corpse-paint influence, dark eyeliner, and an intense, screaming expression. She is gripping a handheld microphone close to her mouth, leaning slightly forward as if screaming, looking slightly off-camera to the left. She is wearing a black gothic stage outfit inspired by Hatsune Miku: a fitted black mini-dress with turquoise trim, leather straps, spiked accessories, black fishnet stockings, dark arm warmers, and heavy black boots. The outfit feels like a black metal reinterpretation of a virtual idol costume, mixing cyber-idol details with gothic and occult stage fashion. The background shows a dark underground metal venue, amplifier stacks, smoke, and harsh backlighting. The stage lighting is dramatic and high-contrast, with cold blue-green highlights catching her hair and warm dim spotlights cutting through haze. The background falls into deep shadows, with mild bokeh from small stage lights and indistinct silhouettes of the crowd. The image has the look of a professional 2005 concert photograph shot on a DSLR, with sharp focus on the performer, slight motion energy, and a gritty live-music atmosphere. @2005 score_8, score_7

sample

Model Details

Downloads last month
453
Inference Examples
Examples
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for Danrisi/UltraReal_FineTune_Anima_base1

Finetuned
(37)
this model