Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
copaxTimeless_xivSDXL.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
Copax
on Civitai
"by Copax - SDXL version - Recommend Steps 25~50 CFG 5~7 You can also use hiresfix or After Detailer Sampling Restart Euler a or DPM 2M ++ SDE Karass Nprompt worst quality, low quality, illustration, 3d, 2d, open mouth, tooth,ugly face, old face, long neck,"
Creator notes
Xplus-2B-NSWF-1 XPlus-2B-1 is a powerful NSFW-focused AI image generation model, specially tuned for creating highly detailed and sensual adult content. It excels in enhanced line sharpness and seamless, continuous linework, delivering crisp, fluid outlines that bring every curve and contour to life with exceptional clarity. Materials render with stunning gloss and realism—think shiny latex, wet skin, metallic sheen, and reflective surfaces that catch light beautifully. Reflection effects are top-tier, with accurate specular highlights, subtle caustics, and dynamic light bounces that add depth and erotic allure to every scene. Steps: 20 CFG: 4 Sampler: dpm_2 karras Nprompt: safe_neg, worst quality, bad quality, low quality, missing fingers, extra fingers, rembrandt lighting, darkness, night, sweat, dutch angle, Qwen-Unreal-NSFW (BF16 40GB) !!! Warning: This version is only suitable for machines with high-end GPUs, or for rented server instances with GPUs offering 40GB+ VRAM. In testing, running on an RTX 3090 (24GB VRAM) was very slow for image generation, while it ran well on an A100. It has not yet been tested on other GPU models. Workflows ComfyUI: Sampler: Euler, Res Multistep Scheduler: Simple, SGM Uniform Steps: 20, 30, 50 CFG: 3.5, 4 Model Sampling Algorithm – AuraFlow Offset: 3.1 Recommended Resolutions: 1152×1536, 992×1776, 928×1984, 1536×2048 (all of the above resolutions can be used in both portrait and landscape orientations) Qwen-Ultra-Realistic-NSFW (BF16 40GB) The first Qwen model to support native 2K resolution output. Outstanding portrait generation capabilities: freely handles males and females, all age groups, single or multiple subjects. Also allows flexible control over strong depth of field, shallow depth of field, or no depth of field effects. Broad applicability: supports multiple textures (film, studio, web-style images, etc.), multiple styles (modern, traditional, fantasy, cosplay, etc.), various special compositions (grid layouts, breaking out of the frame, etc.), and enables stable batch generation for both Chinese and English posters. Workflows ComfyUI: Sampler: Euler, Res Multistep Scheduler: Simple, SGM Uniform Steps: 20, 30, 50 CFG: 3.5, 4 Model Sampling Algorithm – AuraFlow Offset: 3.1 Recommended Resolutions: 1152×1536, 992×1776, 928×1984, 1536×2048 (all of the above resolutions can be used in both portrait and landscape orientations) _________________________________________ XPlus-Z This model is currently in the development phase, and I will continue improving its quality with each upcoming version. Early access is enabled to help generate funding for future development. The model is fine-tuned from and enhanced with additional datasets covering people, backgrounds, details, skin textures, and poses. The current version produces images with higher contrast, reduced noise compared to the base model, and slightly different character appearances, among other improvements. Workflows ComfyUI: - Steps: ~14 - Distilled CFG Scale: 1 - CFG : 1 - Sampling: res_2s - Vae: flux vae - Clip: qwen_3_4b.safetensors N Prompt: over-smooth skin, plastic skin, doll face, anime, CGI, waxy texture, blurry face, fake pores, exaggerated makeup, over-sharpening, unrealistic symmetry, flat lighting, low detail skin, extra fingers, distorted anatomy ComfyUI/models/vae ComfyUI/models/text_encoders Get res_2s sampler - Click the Manager button in the main menu - Select Custom Nodes Manager button - Enter RES4LYF in the search bar - Install ____________________________ XPlus 4 / XPlus_Cartoon Recommend: Distilled CFG Scale(Flux CFG) : Set Flux CFG to around 3 if you want the image to look more realistic with better skin details. Increase Flux CFG to 5 or 6 if you want sharper details, such as more defined hair strands. However, keep in mind that increasing CFG may reduce skin detail and make it look more plastic-like. ____________________________ XPlus MIX 4 Recommend: Distilled CFG Scale(Flux CFG) : 1.9 !!! Note: Mix_4 version includes a faded vintage photo border effect that appears in most generated images. If you don’t like this, please consider it before downloading. _______________________ - - _________________________ Check my models on Mage: - - TimeV10 / - VividXL2 / / _____________________________ --- XPlus 3/ XPlus MIX 3/ XPlus 3 Dark --- - The most noticeable difference between the XPlus 3 and XPlus MIX 3 models is the lighting effect. The XPlus 3 delivers an absolute black tone more effectively, while the XPlus MIX 3 excels at warm tones, providing softer light that highlights facial and skin details more clearly. - For example, in a photo taken in a dark room, the XPlus 3 produces a deeper black background, whereas the MIX 3 makes the face appear brighter and more evenly toned. In outdoor photos under sunlight, the MIX 3 creates a more realistic and natural effect. - Additionally, there are some differences in hair, skin, and material rendering. Finally, the XPlus 3 Dark model is undoubtedly the darkest version, evoking lighting and atmosphere similar to images set in dungeons. The Dark 3 also introduces more noise, making it ideal for dark art, horror themes, and images that require a gloomy atmosphere. _____________________________________________ Copax Timeless ver XPlus 3 (Canny) This is a model combination of the XPlus 3 model and Introducing FLUX.1 Tools by BlackForestLabs: - Note: ComfyUI is required to use this model. Recommend ComfyUI workflow for the model: - Steps: 20 - Distilled CFG Scale: 4.5 - CFG : 1 - Diffusion in Low Bits: float8-e4m3fn - Sampling: Euler simple - Nprompt: none - Vae: flux vae (must have) - Clip: clip_l.safetensors and t5xxl_fp8_e4m3fn.safetensors (must have) _________________________________ Copax Timeless ver XPlus 2 (base train) Note: If you only want to create images, it's not necessary to download this version; you can use other versions of the m
4,878 downloads · 179 likes on Civitai
SHA256
FB3895DC9C22159E0CA9C47B1DACEAA9A54000048EFE066D1EE830B0E42984FD
ModelTrends.ai Model ID
#15953
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
Euler a Karras
Steps
20
Guidance
4
Seed
198129714242290
Size
1440x2496
Prompt
, LEGO, a fish made of LEGO bricks smoking a cigarette, sitting like a human, dark humor, cinematic lighting, detailed plastic texture
Negative prompt
blurry, low quality, worst quality, realistic skin, organic texture, messy proportions, watermark, signature, logo, text, caption, brand name, letters, words, username, artist name, copyright, blurry text, low quality text, embedded text, visible text
Settings
Sampler
DPM++ 3M SDE
Steps
40
Guidance
3.5
Seed
2879733460
Size
896x1152
Prompt
A fish driving a tiny convertible underwater, complete with a license plate that reads 'FIN-FAST,' while an octopus hitchhikes on the side of the road.
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label, long neck
Settings
Sampler
DPM++ 2M SDE
Steps
40
Guidance
5
Seed
2571766349
Size
896x1152
Prompt
A butterfly with wings that dissolve into splashes of vibrant, chaotic paint. The background is an explosion of color and energy, with streaks and splatters creating the illusion of movement. The butterfly appears to be caught mid-flight, as if it is both emerging from and dissolving into the abstract chaos.
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label, long neck
Settings
Sampler
DPM++ 2M SDE
Steps
30
Guidance
7
Seed
4016077210
Size
1152x896
Prompt
Woman in pink tank top and jeans, leaning over hood of vintage car, desert landscape, Warm lighting, long shadows cast across rolling hills, Woman’s expression conveying a mix of focus and determination, Vintage car with classic lines, shape from 1960s or 1970s, Car’s color is a subtle shade of orange, Dry grasses blowing slightly in breeze, Warm earthy tones of pink and brown, Sense of peace,, cinematic lighting, shallow depth of field, rule of thirds, soft focus edges, crisp details, grainy texture, warm color grade, earthy tones, shot with Canon 5D Mark IV, 50mm f/1.4 lens, single point autofocus, aperture priority,
Negative prompt
blurry face, bad facial details, badhadc4, worst quality, low quality, normal quality, lowres, bad anatomy, bad hands, normal quality, text, bad-hands-5, badly drawn face, cropped, mutation, deformed, disfigured, long neck, signature, watermark, artist name, sign, artifacts, fonts, typography, letters, writing, logo, url, words, name,
Settings
Sampler
Euler a Karras
Steps
20
Guidance
4
Seed
966365936472578
Size
1440x2496
Prompt
, LEGO, a shopping cart filled with LEGO food items, supermarket scene, realistic lighting, shallow depth of field, highly detailed
Negative prompt
blurry, low quality, worst quality, realistic skin, organic texture, messy proportions, watermark, signature, logo, text, caption, brand name, letters, words, username, artist name, copyright, blurry text, low quality text, embedded text, visible text
Settings
Sampler
DPM++ 2M SDE
Steps
40
Guidance
5
Seed
2571766352
Size
896x1152
Prompt
A highly stylized portrait of a human face, fragmented into geometric shapes with bold, contrasting colors. The background is filled with angular lines and distorted reflections, creating a dynamic, chaotic energy that conveys emotion through abstraction.
Negative prompt
(worst quality, low quality, normal quality, lowres, low details, grayscale, bw), painting, drawing, sketch, cartoon, anime, manga, render, CG, 3d, watermark, signature, label, long neck
AI Models for Image, Video & Text Generation
copax timeless14 xl is a base model for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models