Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
proteusRundiffusion_withclip.safetensors
6.46 GB · SafeTensor · fp16 · full
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<proteus-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
DataVoid
on Civitai
Creator notes
Introducing Proteus-RunDiffusion In the development of Proteus-RunDiffusion, our team embarked on an exploratory project aimed at advancing the capabilities of AI in art creation. Our journey, inspired by the broad achievements of models like Pony Diffusion v6 XL CLIP, led us to experiment with the CLIP architecture in novel ways. Through a serendipitous process of trial, error, and discovery, we developed a unique approach to retraining CLIP that we hadn't initially set out to achieve. This approach inadvertently unlocked new potentials in character recognition, natural language processing, and, most notably, the versatility of artistic expression. The cornerstone of our discovery, which we refer to as "style unlocking," emerged unexpectedly. This breakthrough allows models that were previously limited to specific genres or styles, such as anime, to generate art across a broader spectrum, including high-fidelity photorealism. This was a result of our reimagined CLIP model's ability to interpret and understand prompts in ways that surpass the original boundaries of style and genre. We have observed that this retraining has also led to significant improvements in handling CFG scaling, effectively broadening the range from 3 to 50 without the previous limitations or failures. This enhancement opens up new avenues for creative expression and technical reliability in AI-generated art. In terms of usage, we recommend a CLIP setting of -2 along with a strategic use of light negatives for optimizing the artistic output of Proteus-RunDiffusion. The CFG setting can vary depending on the project, with 8.5 being ideal for standard requests and 3.5 for more artistic explorations. The model supports and encourages experimentation with various tags, offering users the freedom to explore their creative visions in depth. Using Proteus-RunDiffusion: Expect a Different Experience When you start using Proteus-RunDiffusion, be ready for it to behave differently from other AI art models you've used. It's been designed in a unique way, which means it will respond to your prompts and commands in its own style. This difference is part of what makes it special, but it also means there's a learning curve. You'll need some time to get familiar with how it works and what it can do. So, as you begin, keep an open mind and be prepared to adjust your approach. Importantly, we want to clarify that our development of Proteus-RunDiffusion was inspired by existing works but does not directly incorporate or rework specific components from models like Pony Diffusion's CLIP. Our advancements are the result of our proprietary research and development efforts, aimed at enhancing the creative possibilities and compatibility across different AI art generation platforms. As we continue to refine Proteus-RunDiffusion and delve deeper into its capabilities, we are preparing to conduct a Human Preference Study and to share our findings and methodologies in more detail through upcoming research publications. This model represents not just a technical achievement, but a step towards understanding the broader potential of AI in the creative process, discovered through inspiration and the unexpected turns of research.
3,276 downloads · 274 likes on Civitai
SHA256
8C66571573BE490AE48F139B1F7E457BFA7AEFFD3A35841EF6FE0A71DD7D9991
ModelTrends.ai Model ID
#9281
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
DPM++ SDE Karras
Steps
12
Guidance
7
Seed
695235131
Size
1024x1024
Clip skip
7
Prompt
stylized by beeple, noah bradley, cyril roland and ross tran, photograph, [Prehistoric:Steerage:3] (bathysphere:1.3) , the bathysphere is Grotesque and Fairy-Tale, made from Red oak, shallow depth of field, detailed architecture, 2D flat anime, natural lighting, geometric shapes, feminine mystique, wooden tabletop, enchanted, sharp focus, complex artistic color composition, badge, sunny, extremely rich detail, masterpiece, best quality,
Negative prompt
full body shot, painting, illustration, industrial, mechanical, geometric patterns, (photorealism:1.3), simplistic, minimalism, plain, simple, bright, sunny, light, vibrant, colorful, (realism:1.3), modern, ordinary, mundane, abstract, camera, cartoon, sketch, 3d, render, worst quality, low quality, western cartoon, rustic, primitive, organic, masculine, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art, watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name, blur, blurry, grainy, ugly, asymmetrical, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate,, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry
Settings
Sampler
DPM++ 3M SDE Exponential
Steps
60
Guidance
20
Seed
3395868042
Size
1024x1536
Clip skip
2
Prompt
the most vibrant AI generated image of a female ever, score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up
Negative prompt
deformed
Settings
Sampler
DPM++ 2M SDE Karras
Steps
30
Guidance
7
Seed
198217990
Size
1024x1024
Clip skip
2
Prompt
masterpiece, best quality, absurdres, highres, very aesthetic, icy flower, night, dim light, no humans, macro shot, highly detailed, flower made of ice,
Negative prompt
worst quality, low quality, normal quality, lowres, jpeg artifacts, bad anatomy, error, long neck, ugly,
Settings
Sampler
DPM++ 3M SDE
Steps
50
Guidance
4
Seed
360663251
Size
1152x896
Clip skip
2
Prompt
Award winning photograph of an alien planet where the boundaries between reality and imagination blur effortlessly. Each step unveils a symphony of colors and textures dancing in harmony. A vast, ethereal valley. As you gaze across the expanse, you're greeted by rolling hills adorned with lush alien foliage, each blade of grass shimmering with dewdrops like scattered jewels. In the distance, towering spires of crystalline structures rise from the earth, their surfaces reflecting the golden hues of an eternal sunset. Liquid light cascades down their facades, pooling into crystalline lakes that mirror the star-strewn heavens above. As you traverse this otherworldly landscape, you find yourself drawn deeper into its embrace, each step revealing new wonders and delights. Glowing flora illuminate your path, casting a kaleidoscope of colors upon the ground. Above, wisps of iridescent clouds drift lazily across a cerulean sky, morphing and shifting like dancers in an endless ballet. The pink sun, a radiant orb of warmth and light, bathes the land in its golden embrace, casting long shadows that dance across the landscape like playful spirits. Here, amidst the beauty of the dream landscape, you find solace and serenity, a sanctuary for the soul to wander and explore to its heart's content. Vibrant color, realistic lighting, detailed shadows, planet visible in sky, score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, <lora:RMSDXL_Creative:2> <lora:RMSDXL_Enhance:2> <lora:xl_more_art-full_v1:.8>
Negative prompt
(worst quality, low quality), crayon, graphite, abstract, glitch, deformed, mutated, ugly, disfigured,
Settings
Sampler
DPM++ SDE Karras
Steps
10
Guidance
3.5
Seed
1442610004
Size
832x1224
Prompt
serenade of a (lonely:1.1) crying smiling wolf quivering under a cold blanked mourning a fallen friend, beautiful melancholic (solo:1.1) concert, depressive tears of silver, (sad:1.3) lines of a mountain mirror, (howling:1.3) at a sky beyond, moon, bittersweet faithful night, <lora:- SDXL - vanta-black_contrast_V3.0:0.8> <lora:Moody__Time:0.7>, <lora:Desolation:0.5>
Settings
Sampler
DPM++ SDE Karras
Steps
15
Guidance
5
Seed
667748029
Size
824x1216
Prompt
crocodile blue alight, calm, covered longing for blanked, feathered, composition, shadows from a cloud, <lora:SDXL - Style - EldritchRomanceIllustration1.3.1:0.8>, <lora:- SDXL - vant_blk_contrast_V2.0:0.8>, <lora:sss:0.8>, <lora:artfullyECHELIER_SDXL_V1:0.8> <lora:DonMP41n717Bl4ckXL:0.8> <lora:- SDXL - dragon_demon_variation_V1.0:0.6>
Negative prompt
SDXL_TI_my_eyes_are_bleeding_2.0, overlapping,
AI Models for Image, Video & Text Generation
proteus 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