Tensor.Art

FilmGirl 胶片风 Film Grain LoRA

LORA
Original


Updated:

blur image
<lora:FilmVelvia3:0.6>, A girl in a modern, elegant ball gown, styled with a sleek updo and minimalist jewelry. She should have a confident, regal expression. The background is a luxurious modern palace, with clean lines, high ceilings, and extravagant chandeliers. The photo should be shot in high definition, with a sharp focus on the subject and a soft, blurred background for a captivating portrait
  • <lora:FilmVelvia3:0.6>, A girl in a modern, elegant ball gown, styled with a sleek updo and minimalist jewelry. She should have a confident, regal expression. The background is a luxurious modern palace, with clean lines, high ceilings, and extravagant chandeliers. The photo should be shot in high definition, with a sharp focus on the subject and a soft, blurred background for a captivating portrait
  • <lora:FilmVelvia3:0.6>, 1girl, abstract 1998 european blond hiphop girl by sachin teng x supreme, attractive, stylish, designer, orange, asymmetrical, geometric shapes, graffiti, street art, cowboy shot, ray tracing,
  • <lora:FilmVelvia3:0.6>, fashion photography portrait of 1girl, offshoulder, fluffy short hair, soft light, rim light, beautiful shadow, low key, (photorealistic, raw photo:1.2), (natural skin texture, realistic eye and face details), hyperrealism, ultra high res, 4K, Best quality, masterpiece, necklace, (cleavage:0.8), in the dark
  • <lora:FilmVelvia3:0.6>, masterpiece, best quality, 1girl, solo, sexy pose, pensive woman, voluminous dress, intricate lace, embroidered gloves, feathered hat, curled hairdo, pale skin, minimal makeup, tender smile, dainty neckline, nostalgic atmosphere, still life
  • <lora:FilmVelvia3:0.6>, a portrait photography of a gorgeous redhead in open unbuttoned white space suit, cleavage, standing inside spaceship, attractive, flirting, looking at viewer, detailed skin, highly detailed, diffused soft lighting, hyperrealism, cinematic lighting
  • <lora:FilmVelvia3:0.6>, 1girl, Textured garments, poised poise, dramatic angles, geometric shapes, contrasts of light and shadow, slick futurism, avant-garde styling, high-tech backdrop, crisp lines, ultra-high resolution
  • <lora:FilmVelvia3:0.6>, 1girl, Floral motifs, luminous skin, enchanting gaze, embellished attire, natural lighting, shallow depth of field, romantic setting, dreamy pastel palette, whimsical details, captured on film
  • <lora:FilmVelvia3:0.6>, Best portrait photography, RAW photo, 8K UHD, film grain, cinematic lighting, elegant 1girl, offshoulder dress, (natural skin texture), intricate (fishnet stockings), forest, natural pose, embellishments, cinematic texture, 35mm lens, shallow depth of field, silky long hair
  • <lora:FilmVelvia3:0.6>, The model's bust is composed entirely of pieces of multi-colored hard candy stacked together. Her facial features are stylized with different flavors and colors of candy - red lips, blue eyes, yellow hair. A few pieces come loose and dangle down, about to drop off. It's a sweet, playful and whimsical interpretation of her portrait. (RAW photo, best quality),(realistic, photo-realistic:1.3), clean, masterpiece,finely detail,masterpiece,ultra-detailed,highres,(best illustration),(best shadow),intricate, bright light
  • <lora:FilmVelvia3:0.6>, A young woman stands on a weathered wooden dock extending over a still mountain lake at dusk. Dressed in cutoff denim shorts and a loose white tank top, she gazes pensively over the glassy waters with hands in her pockets. Her long honey-blonde hair glows in the golden light of the setting sun. A sense of peace and solitude pervades this high alpine scene at day's end as the sky fades into pastel hues and the loons begin their plaintive calls
  • <lora:FilmVelvia3:0.6>, young 1girl with braided hair and fluffy cat ears, dressed in Off-Shoulder Sundress, standing in a rustic farm setting. She has a soft, gentle smile, expressive eyes and sexy cleavage. The background features a charming barn, fields of golden wheat, and a clear blue sky. The composition should be bathed in the warm, golden hour light, with a gentle depth of field and soft bokeh to accentuate the pastoral serenity. Capture the image as if it were taken on an old-school 35mm film for added charm, looking at viewer
  • <lora:FilmVelvia3:0.6>, fashion photography portrait of woman avatar, 1girl in blue lush Alien Rainforest with flowers and birds, fantasy, octane render, hdr, Dolby Vision, (intricate details, hyperdetailed:1.2), (natural skin texture, hyperrealism, soft light:1.2), fluffy short hair, , sharp focus, night, necklace, Chinese mythology, cleavage, medium breasts, sci-fi headband, looking at viewer, best quality, perfect body
  • <lora:FilmVelvia3:0.6>, Classic Hollywood glamour, girl in a stunning red evening gown, dazzling accessories, (captivating eyes, red lips, flawless skin), luxurious backdrop, velvet curtains, dramatic pose, interesting composition, spotlight illumination, rich shadows, shallow depth of field, sparkling bokeh, exquisite details, high-resolution, 35mm film, timeless elegance. portrait photography, 35mm film, natural blurry
  • <lora:FilmVelvia3:0.6>, 1girl, solo, outdoor, cute japanese model girl, kimono, floral print, hair ornament, looking at viewer, hair flower, brown eyes, bangs, masterpiece, best quality, realistic
  • <lora:FilmVelvia3:0.6>, 1girl, Textured garments, poised poise, dramatic angles, geometric shapes, contrasts of light and shadow, slick futurism, avant-garde styling, high-tech backdrop, crisp lines, ultra-high resolution
  • <lora:FilmVelvia3:0.6>, Best portrait photography, 35mm film, natural blurry, 1girl, sun dress, wide brimmed hat, radiant complexion, whimsical pose, fluttering hair, golden sunlight, macro shot, shallow depth of field, bokeh, dreamy

This is a LoRA model for generating film-style AI portrait photos, with over 60,000 downloads on Civitai and widely praised by users.

When used in combination with photorealistic models such as majicMIX realistic, MoonMIX, or Chilloumix, this model can produce realistic film-style photos. It is also recommended to use it in conjunction with TEXTUAL INVERSION models: bad_pictures and negative_hand Negative Embedding. These two Negative Embedding models will not significantly affect the texture of the film.

The currently uploaded Velvia 2.0 version is the latest in the film-style series and offers the most balanced blend of film texture and facial effects. Updates in this version include:

  • The image resolution of the main LoRA model's training dataset has been further increased to 768x1152.

  • During the training of the main model, 15 Asian young male film training photos were added to improve the model's realism when generating male photos.

  • Based on the high-resolution main model, a small proportion of the well-reviewed Filmgirl historical version models from the previous two versions have been blended. After multiple tests, this blended model operation can reduce the LoRA model's impact on facial shapes.

这是一个用于生成胶片风格AI写真照片的LoRA模型,C站上下载量已近6万,广受大家好评。

该模型与majicMIX realisticMoonMIX或Chilloumix等写实模型搭配使用,可以生成逼真的胶片风格照片。同时推荐搭配TEXTUAL INVERSION模型bad_picturesnegative_hand Negative Embedding这两个Negative Embedding模型不会显著影响到胶片的质感。

目前上传的Velvia 2.0版本是胶片风系列模型的最新版本,也是胶片质感与面容效果最为平衡的版本。该版本的更新内容包括:

  • Velvia 2.0的主体LoRA模型的训练集图像分辨率进一步提升至768*1152。

  • 本版本主体模型训练时,加入了15张亚洲年轻男性胶片训练照片,以提高模型在生成男性照片时的真实感。

  • 在高分辨率主体模型基础上,少比例融合了之前两版评价良好的Filmgirl历史版本模型。经过多次测试,这样融合模型的操作可以减少LoRA模型对脸型的影响。

684,814
Runs
572
Downloads
Uploaded
Base ModelSD 1.5

2023.7.8 Introducing "The VELVIA 3.0" 更新内容: Velvia 3.0的主体LoRA模型的训练集图像数量已达到406张,分辨率进一步提升至1024*1024。 本版本主体模型训练使用了Scale weight norms功能,以避免模型过拟合。在另一个备用版本中我也测试了“Prodigy” Optimizer, 这个Optimizer可以在一半的训练总步数下提供与AdamW8bit相当的拟合程度,但可能是我参数设置不合适,训练结果的人脸美感较差,因此最终没有采用。 在高分辨率主体模型基础上,少比例融合了Velvia 2.0模型,同时进行了分层调节,以改善人像肤色。 Update Content: The number of training images for the main LoRA model of Velvia 3.0 has reached 406, with the resolution further increased to 1024x1024. In this version, the main model training utilizes "Scale weight norms" functionality to avoid overfitting. I also tested the "Prodigy" Optimizer in another alternative version. Prodigy can provide a fitting degree comparable to AdamW8bit with half the total training steps, but perhaps due to inappropriate parameter settings, the facial aesthetics of the training results were not as good, so it was not adopted in the end. Based on the high-resolution main model, a small proportion of the Velvia 2.0 model was blended, and hierarchical adjustments were made to improve the skin tone in portraits.

  • Download the model file

  • Use without crediting

  • Share merges of this model

  • Use different permissions on merges

Commercial use: None

Comments

Related Posts