ulp flux — modelo de IA FLUX

Torrents are shared peer to peer by their seeders; ModelTrends.ai hosts no files. Open the magnet link with a BitTorrent client and compare the finished file's checksum with the one on the listing.

BitVector

PirateDiffusion

Instalar / Ejecutar en Graydient

Requiere membresía

<ulp-flux>

Sobre este modelo

FLUX · LoRAs

Creado por

Danrisi

en Civitai

By:Danrisi Ultrarealistic Lora Project The main goal was to make more 'live' images with livelier emotions and more dynamic poses and slightly amateurish quality (also can produce high quality images).

Notas del creador

The main goal was to make more 'live' images with livelier emotions and more dynamic poses and slightly amateurish quality (also can produce high quality images). P.S: Thanks to everyone for the feedback! I've noticed the comments (not only here) about anatomy issues, and I’ve been collecting reports and examples from all of you. I'm considering a couple of options to address this: - Training a full checkpoint, which might be the more rational approach for consistent improvements. - Expanding the dataset with more photos that cover diverse poses to help refine anatomical accuracy. I appreciate the input - it really helps me shape the future updates P.S.2: I’ve moved training to RunPod for consistent, high-quality results. If you'd like to support my work and future updates, you can find me on Ko-fi. Cause i plan to fine-tune a model, not just a LoRa. Setting i use in ComfyUI for Flux: CFG=1, Guidance =2.5, Scheduler=Beta, Sampler=dpmpp_2m, Steps=40, Strength= from 0.8 to 1.0 works good, but i'm usually use with 1, but if hands getting worse then i set 0.87 Setting i use in ComfyUI for SD3.5: CFG=1, Guidance =3.5, Scheduler=sgm_uniform, Sampler=dpmpp_2m, Steps=40, Strength= from 0.5 to 1.0 works good, but i'm usually use with 0.7 V2 - Flux Brings even more realism and versatility to your creations, with significant improvements in stability, anatomy, and overall quality. This update makes the LoRA more adaptive, allowing you to achieve various quality levels based on your prompts—from high-definition realism to intentionally lower-quality aesthetics. Trained on 1048 images. What's New: Stability Improvements: The new version is more stable and works better with text-based prompts, providing a smoother and more predictable output. Enhanced Hands & Anatomy: Hands and body anatomy are more refined, enhancing lifelike quality. Quality Flexibility: With the right prompts, you can adjust for both high-quality and lower-quality aesthetics (examples available). V1.2 for SD3.5 - Large Decided to make a version for sd3.5 almost with same settings. Imo looks good, but i noticed some problems with anatomy (in some moments even worse then flux), but aesthetic (colors, contrast and other stuff looks even better then flux). I see that sd3.5 have potential, maybe new versions will be on sd3.5 too. V1.2 Changed half of images in dataset, changed prompting style, improved hands, less 'flashlight effects' at night scenes and overall LoRa quality improvement (i hope). In this version it's unnecessarily to use tons of 'trigger words' like in V1. Just add some of them that i mentioned in trigger words V1 Trained another amateur lora (that's already been done a lot around here). Still, I took some pictures from my dataset on the 2000s and added another 700 pictures. It came out pretty good so far, but there is a controversial point about quality optimization, I was hoping it would help control the quality, but as I see it only confused the model. In the dataset there are many different gradations of quality, like: 1) High-resolution photo, shot on a mobile phone, no visible artifacts, clear and sharp 2) Low-resolution, amateur photo shot on digital camera, no visible jpeg artifacts, slightly noisy 3) Medium-resolution photo, shot on a mobile phone, slight graininess due to low light conditions, no significant digital artifacts And other their combinations and variations. I think i'll remove such in next version. But this one working the best for me: Low-resolution, amateur photo shot on digital camera, no visible jpeg artifacts, slightly noisy

Palabras de activación

amateurish photo

low lighting

in motion

overexposed

underexposed

GoPro lens

eerie atmosphere

smeared background

smeared foreground

67,160 descargas · 3,150 me gusta en Civitai

SHA256

B1C4DDF95671E6B51817B4F3802865E544040C232C467E76B1CB0C251BD6B634

ID de modelo de ModelTrends.ai

#20869

Denunciar contenido

Renders de ejemplo

Prompts y ajustes compartidos por quienes hicieron estos renders en Civitai. Elige un render para ver cómo se hizo.

Obtener este prompt

Render de Graf137 en Civitai

Reportar

Ajustes

Sampler

Undefined

Pasos

Guidance

3.5

Semilla

529876096

Tamaño

832x1216

Clip skip

Peso usado

0.5

Prompt

A hyper-realistic hauntingly beautiful dark sci-fi scene featuring a vast, barren landscape with a colossal, organic, yellow spherical object. A sphere made up of intertwined and fused egg spheres, intertwined veins and layered flesh reveals a structure of fused mutated spheres and intertwined veins and sinews. A woman in a yellow biohazard suit stands on rocky terrain, staring at the mysterious sphere. An overcast sky hangs over her, creating an eerie atmosphere on the desert landscape. In the distance, man-made structures can be seen on the horizon, hinting at a wider world, sci-fi and high tech. This striking image evokes a sense of wonder and curiosity, inviting viewers to explore the mysterious world that lies within, cinematic, painting, high definition, high detail, 16K resolution. ultra sharp focus photo, 3d render, architecture, dark fantasy, vibrant (photography, high-resolution, dynamic, energetic,hyper-realistic, dramatic lighting, shallow depth of field.)

Render de miskinetto en Civitai

Reportar

Ajustes

Sampler

Undefined

Pasos

Guidance

Semilla

761997001

Tamaño

832x1216

Clip skip

Peso usado

0.9

Prompt

full length photo, sensual elite woman, sexy attire, photorealistic, boudoir photography, artistic photo, seductive elite woman, sensual nymphomaniac woman, sexy long blue hair with dark highlights, goddess of office, seductive makeup, black eyeshadow, black eyeliner. red nail polish. realistic skin. an unique woman with full of sensuality and attractiveness. stylish full length long black knit sweater with red detais that goes down to knees, one shoulder exposed, sitting on a black leather armchair, stylish golden nylon thigh highs, stylish black high heel shoes. black haired european woman, pale skin, sexy haircut. slightly curvy body, blush, seductive image,serene, untouched beauty, lovely, detailed face, full body accent, seductive lips and makeup , blue eyes, sensual look, night time, background of a luxury mountain cabin with fireplace, room with old style decoration. low lighting, sfw, raw, film grain, low key lighting, shot on Leica T, Miles Aldridge style photo, sensualism. enthusiastic woman. dramatic light, dark background, shadows,Amateur photo, soft film grain, natural lighting, Natural detailled skin, skin pores

Render de miskinetto en Civitai

Reportar

Ajustes

Sampler

Undefined

Pasos

Guidance

Semilla

761996999

Tamaño

832x1216

Clip skip

Peso usado

0.9

Prompt

Render de miskinetto en Civitai

Reportar

Ajustes

Sampler

Undefined

Pasos

Guidance

Semilla

1194612644

Tamaño

832x1216

Clip skip

Peso usado

0.9

Prompt

hyper realistic, 4k, high res, photorealistic, close up, in a sensual bedroom room, at night, sensual golden light. 1 female, pale white skin, long straight ginger slightly messy hair, perky medium breasts, cleavage, wearing sexy black v-neck halter top, and black long dress with slit. black sexy high heel shoes. full cleavage, gold hoop earrings, thin, cowboy shot, slightly smiling with lipstick.

Render de Danrisi en Civitai

Reportar

Ajustes

Sampler

DPM++ 2M

Pasos

Semilla

272622940633580

Tamaño

1216x832

Prompt

amateur photo, low-lit, overexposure, Low-resolution photo, shot on a mobile phone, nighttime, noticeable noise in dark areas.portrait of young woman, early 20s, amateur quality, outside, overexposed, front view, looking at the viewer, She has light skin and dark hair styled in two pigtails, with bangs covering her forehead, She also has a black choker and a black cross necklace, adding to the gothic aesthetic. Her expression is neutral, right hand near the neck. The background shows a room with furnitures and desk with computer and monitor. Left hand holding a sign with handwritten text "The most realistic LoRA". Indoors, low lighting, muted color tones

Render de miskinetto en Civitai

Reportar

Ajustes

Sampler

Undefined

Pasos

Guidance

Semilla

1194612645

Tamaño

832x1216

Clip skip

Peso usado

0.9

Prompt

Guías para este modelo

Modelos

Proyecto UltraRealista LoRA (ULP) v2: fotos espontáneas y estilo amateur en Flux

El Proyecto UltraRealista LoRA de Danrisi hace que las imágenes en Flux parezcan fotos reales: poses más vivas, luz imperfecta, textura honesta. Aprende sus frases clave, peso y ajustes, y ideas para fotos cotidianas creíbles.

Modelos similares

Badges for creators

Made this model? Put its standing on your Civitai page, your Hugging Face card, your README or your site. Each badge is a small picture that shows the standing on the day you copy it and never changes afterwards, however the rankings move later. The date is part of the badge.

Modelos de IA para generar imagen, vídeo y texto

ulp flux es un LoRA para la familia Flux listado en ModelTrends.ai, un catálogo de solo lectura de modelos de IA de imagen, vídeo y texto de código abierto. Compáralo con otros modelos Flux, consulta su puntuación de calor para ver su tendencia y ábrelo en PirateDiffusion o BitVector para probarlo.

Más modelos Flux Más LoRAs de Flux photography realistic poses effects artstyles women girls sexy

Explorar por familia de modelos