Model
Trends
.ai
Model
Trends
.ai
những mô hình AI mã nguồn mở tốt nhất
Chạy cục bộ
leosamsHelloworldXL_filmGrain20.safetensors
4.81 GB · SafeTensor · fp16 · full
Tải xuống do Civitai cung cấp. Một số tác giả yêu cầu đăng nhập Civitai trước.
AD
<moonfilm2>
Về mô hình này
STABLE DIFFUSION 1.5 · Mô hình cơ sở
Tạo bởi
LEOSAM
trên Civitai
LeoSam's MoonFilm version Film Grain 2 is an SD15 realistic analog style photography model for creating Asian personas with a cinematic look
Ghi chú của tác giả
🖥️Welcome to try out the open-source , developed by my friend and me. It offers a one-click installation and comes integrated with multiple features including image pre-compression, image tagging, and tag statistics. Recently, we also launched the of this tool, everyone is welcome to use it! 🌍欢迎加入QQ群"兔狲·AIGC梦工北厂"，群号 ：780132897 ；"兔狲·AIGC梦工南厂"，群号 ：835297318（入群答案：兔狲）。Telegram群聊“兔狲的SDXL百老汇”，链接： 📖HelloWorld 7.0 Update - June 13, 2024 One-sentence update summary: HelloWorld 7.0 is an iteratively optimized version, with the best body performance in the entire series, and further enhanced concept scope and detail richness. Update details: - By adding negative training images, strengthening pose training, and optimizing the clip model, the accuracy of the model's limbs and hands has been improved compared to previous versions. The recommended negative prompt words are: "bad hand, bad anatomy, worst quality, ai generated images, low quality, average quality". - Extracted the fine-tuned LoRA from the and incorporated it into HelloWorld 7.0. SPO is a further improvement of the DPO method. The SPO base model is used for better performance than the DPO XL base model and the original SDXL base model. The SPO LoRA can enhance image details & contrast and beautify images. Thanks to the technical team behind SPO. - Continued to expand the concept scope of the training set, but optimized and streamlined the training set (large training set fine-tuning is too expensive, and H800 is difficult to rent recently, can't afford the local training time). The current total training set is 20,821 images. The training set resolution distribution is as follows, and it is recommended to use several resolutions with a larger number of images for output: (832, 1248) - Count: 7128 (896, 1152) - Count: 6250 (1248, 832) - Count: 2402 (1024, 1024) - Count: 1639 (1360, 768) - Count: 928 (1152, 896) - Count: 870 (768, 1360) - Count: 432 (960, 1088) - Count: 506 (992, 1056) - Count: 162 (1088, 960) - Count: 140 (704, 1472) - Count: 120 (1056, 992) - Count: 122 (1472, 704) - Count: 115 (1632, 640) - Count: 75 (640, 1632) - Count: 12 - Used GPT4O to re-label all datasets. This time, a structured labeling method was used, with the specific structure being: "one-sentence summary description + multiple image element tags + inspired by XXX + aesthetic quality description words", where the aesthetic quality description words are divided into five levels: worst quality, low quality, average quality, best quality, and masterpiece. A typical labeling example is as follows: conceptual art featuring a human hand wrapped in red and beige ribbons, isolated against a plain, light background, realistic style, minimalist color scheme, smooth textures, elongated and surreal aesthetic, inspired by salvador dalí's surrealist works, masterpiece The "High-Frequency Tagging Word List" and the "High-Frequency Art Style List" involved in the Inspired by XXX for the HelloWorld 7.0 version will only be provided to commercial licensing users. Partners who have purchased Helloworld XL series model authorization in the past, please contact me if there are any omissions to get it for free. Players can refer to the . In addition, I have also provided 150+ high-quality HelloWorld 7.0 example images in the gallery, which can be used as a reference for everyone's output. Model making is not easy, thank you players for your understanding and tolerance! 📖HelloWorld 6.0 Update - April 20, 2024 Thank you for your patience. I have been job hunting recently, which caused some delays in the HelloWorld updates. Here are the main updates in version 6.0: - HelloWorld 6.0 is an iterative improvement based on version 5.0. Based on my own testing, the realism effect is not significantly different from version 5.0. The main advantage of version 6.0 lies in its broader coverage of concepts in the training set. According to feedback, enhancements have been made in various themes including surrealism, boudoir, group photos, masks, origami, 3D renders, cars, dragons, and maternity photography. Some examples are provided in the illustrations. - HelloWorld 6.0 intentionally includes some low-quality images in the training to enhance the model's response to negative prompts. It is recommended to use the following terms in negative prompts: "low quality, jpeg artifacts, blurry, poorly drawn, ugly, worst quality". - The main body of the HelloWorld 6.0 training set employs GPT4v tagging. For images that GPT4v cannot tag, cogVQA guided by blip2-opt-6.7b is used for tagging. The tagging language style of these multimodal models differs significantly from the traditional WD1.4 tagger. To facilitate more accurate triggering of different concepts in the training set, I have compiled the top 250 high-frequency tagging words from the HelloWorld 6.0 training set. You can view these high-frequency words in. Finally, although SD3 is about to be released, I will still update to HelloWorld XL 7.0, hoping to achieve greater enhancements in version 7.0! 📖2024.2.22 Introducing "HW5.0_Euler_a_Lightning" This model is a run-accelerated version of the HelloWorld SDXL base model, incorporating both technologies. Equipped with the Eular a sampler and CFG 1, it is capable of generating images in 6-8 steps, which is three times faster than the original SDXL version. Moreover, upon comparison, its imaging results are superior to those of LCM or Turbo versions. The recommended parameters for generating images with this model are: Sampler: Eular a (Important! The model is specifically adapted to Eular a, other samplers may not yield as good results) CFG scale: 1 Sampling steps: 8 steps (6~8 steps are acceptable) Hires algorithm: ESRGAN 4x / 8x_NMKD-Faces_160000_G Hires Upscale factor: 1.5x Hires steps: 8 steps Hires Denoising strength: 0.3 📖2024.2.11 Introducing "HelloWorld 5.0 GPT4V" HelloWorld 5.0 is the most substantial update in the history of the HelloWorld series, tagged wit
33,798 lượt tải · 2,714 lượt thích trên Civitai
SHA256
FE54B5D04D5D55991B19CD120CC21F1161A1941EB85C5645E5813FD900F8B617
ID mô hình ModelTrends.ai
#7955
Báo cáo nội dung
Ảnh mẫu
Prompt và thiết lập do những người tạo ra các ảnh này trên Civitai chia sẻ. Chọn một ảnh để xem nó được tạo như thế nào.
Thiết lập
Sampler
DPM++ 2M
Số bước
20
Guidance
7
Seed
1063663774
Kích thước
512x768
Prompt
cinematic photo of {prompt}, photograph, film, best quality, highres, RAW photo, subject, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3, begging for buzz, looking for buzz
Prompt phủ định
drawing, painting, sketch, bad quality, low resolution, blurry, completely nude, negative_hand-neg, deformed, distorted, open mouth
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
27
Guidance
7
Seed
3031257454
Kích thước
512x832
Clip skip
2
Prompt
yper realistic,metal,professional photo of a futuristic muscle car with multiple modifications, large wheels, driving, cybernetic hood, cyber car parts, front pop up headlights, science fiction, sci-fi scenario, (night), natural light, cyberpunk, futuristic city, cyberpunk city, neon signs, highly detailed, (highly detailed background), multiple buildings in the background, detailed textures, wide angle, 8k, HDR, professional photoshoot, high quality photo, realistic photo, realistic shadows, detailed shadows, realistic proportions,film grain, raw photo,(front)
Prompt phủ định
(worst quality, low quality, bad_pictures, negative_hand-neg:1.2)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
27
Guidance
7
Seed
4082002690
Kích thước
512x832
Clip skip
2
Prompt
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
Prompt phủ định
(worst quality, low quality, bad_pictures, negative_hand-neg:1.2)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
27
Guidance
7
Seed
284786876
Kích thước
512x832
Clip skip
2
Prompt
simple background,(Wearing a female police uniform and a police cap:1.4), good hand,4k, high-res, masterpiece, best quality, head:1.3,((Hasselblad photography)), finely detailed skin, sharp focus, (cinematic lighting), soft lighting, dynamic angle, [:(detailed face:1.2):0.2],midriff peek, medium breasts, breasts,(((inside mansion))),1girl, jewelry,earrings, orange_sky, solo, long_hair, upper body, grey eyes, looking at viewer,black hair,Fashion,(head tilt:1.4), red background, lips, slightly smile
Prompt phủ định
(worst quality, low quality, bad_pictures, negative_hand-neg:1.2)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
27
Guidance
7
Seed
2866436459
Kích thước
512x832
Clip skip
2
Prompt
scenery,absurdres,hyper realistic lifelike texture dramatic lighting unrealengine trending on artstation,award winning photo,nikon RAW photo,8k,Fujifilm XT3,masterpiece,no humans, ,cold, winter, mountain, fog, lut, cinematic, dimmed colors, dark shot, muted colors, film grain, ice,iceland,aurora,
Prompt phủ định
(worst quality, low quality, bad_pictures, negative_hand-neg:1.2)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
27
Guidance
7
Seed
86301180
Kích thước
512x832
Prompt
otherworldly-scene, titanic-geysers, hair-raising-atmosphere, alien-weather-systems, 9:16-vertical-frame, hypnotic-landscapes, ultra-realistic-surfaces, contrasting-lights, trending-artstation, honored-creation, Panasonic-Lumix-S1R, 8k-resolution, peaceful, no-humans, extraterrestrial-geysers, towering-plumes, metallic-terrain, shimmering-colors, iridescent-clouds
Prompt phủ định
(worst quality, low quality, bad_pictures, negative_hand-neg:1.2)
Thiết lập
Sampler
DPM++ 2M Karras
Số bước
27
Guidance
7
Seed
3078076885
Kích thước
512x832
Prompt
extraterrestrial-environment, immense-crystals, oppressive-ambience, alien-storms, vertical-9:16-layout, captivating-vistas, vivid-textures, dramatic-shadows, popular-on-artstation, prize-winning-image, Sony-Alpha-7R-IV, 8k-quality, tranquil, no-humans, otherworldly-horizon, crystal-forest, electric-haze, contrasting-colors, shifting-sky
Prompt phủ định
(worst quality, low quality, bad_pictures, negative_hand-neg:1.2)
Mô hình AI để tạo hình ảnh, video & văn bản
moonfilm2 là một mô hình cơ sở thuộc họ Stable Diffusion 1.5 được liệt kê trên ModelTrends.ai, danh mục chỉ đọc về các mô hình AI hình ảnh, video và văn bản mã nguồn mở. So sánh nó với các mô hình Stable Diffusion 1.5 khác, xem điểm độ hot để biết xu hướng và mở trên PirateDiffusion hoặc BitVector để dùng thử.
Duyệt theo họ mô hình
Duyệt tất cả mô hình