Model
Trends
.ai
Model
Trends
.ai
ang pinakamahuhusay na open source AI model
Patakbuhin nang lokal
albedobaseXL_v12.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Ang mga download ay mula sa Civitai. May mga gumawa na humihingi muna ng Civitai login.
AD
I-install / Patakbuhin sa Graydient
Nangangailangan ng membership
<albedo-xl>
Tungkol sa model na ito
STABLE DIFFUSION XL 1.0 · Mga base model
Ginawa ni
albedobond
sa Civitai
AlbedoBase XL v1.2 model by albedobond
Mga tala ng gumawa
If you've found value in the model, please consider offering your support. Your contribution will be devoted entirely to advancing the SDXL community. ㅤ|ㅤ ㅤ |ㅤ AlbedoBase XL (SFW&NSFW) The refiner is unnecessary, and VAE is included. GOAL Stable Diffusion XL has 3.5 billion parameters (excluding the Refiner), which is about 3.6 times more than the SD v1.5 version. I believe that this is not just a number, but a number that can lead to a significant improvement in performance. It has been a while since we realized that the overall performance of SD v1.5 has improved beyond imagination thanks to the explosive contributions of our community. Therefore, I am working on completing this AlbedoBase XL model in order to optimally reproduce the performance improvement that occurred in v1.5 in this XL version as well. My goal is to directly test the performance of all Checkpoints and LoRAs that are publicly uploaded to Civitai, and merge only the resources that are judged to be optimal after passing through several filters. This will surpass the performance of image-generating AI of companies such as Midjourney. As of now, AlbedoBase XL v3.1 Large has merged about 200 selected checkpoints and 251 LoRAs. LOG v3.1-Large • Merged over 50 selected latest versions of SDXL models using the recursive script employed in V3. The spec grid(370.7 MB): v3-mini I sincerely apologize for keeping you waiting for such a long time. I’ve been dealing with some personal matters, and while working on the new version, I also faced health issues. Even as I write this, I am still struggling with these challenges. I felt it wouldn’t be enough to just provide a brief update, so I kindly ask for your understanding as I share this more detailed message. Since the release of version 2.0, I have been dedicating myself to studying deep learning independently. I don’t have a formal degree, and apart from a modest aptitude for programming, only my background is in the arts. As a result, I lack the mathematical and scientific foundation to achieve significant breakthroughs, given the time and effort I’ve invested. Despite this, the experience of immersing myself in this self-directed study and research has been an invaluable treasure in my life. Recently, I stumbled upon an idea that could potentially be a significant breakthrough. After reworking hundreds of formulas and methods since version 2.0, I managed to develop a rather intriguing and successful algorithm. The model merging process was based on SDXL1.0 and SD1.5, along with other carefully curated models. These were categorized into five primary classifications: “ANIME,” “REALISM,” “ARTISTIC,” “NSFW,” and “BASE,” and fed into the merging algorithm as datasets. This approach has resulted in some fascinating outcomes. However, as challenging as the algorithm development was, nothing has been as daunting as the performance testing phase. My physical and mental health deteriorated significantly during this period, to the point where I realized I couldn’t continue this work on my own. This is what ultimately led me to decide to release this version. And now, I am thrilled to announce the release of the much-anticipated AlbedoBaseXL V3 Mini version. While this model is a smaller-scale merge, it is not limited to any specific area and performs remarkably well across various domains. It has the potential to serve as a new base model for SDXL1.0. (For reference, my merging algorithm is not a “linear merging,” so it can essentially be considered a new fine-tuned model.) This model, along with the existing AlbedoBase models, is versatile and surpasses all previous versions in every aspect. (The NSFW content, while not extreme, offers a broader range of expression compared to previous versions like v2.1. A dedicated NSFW merging model will be released in the future.) On another note, I’ve noticed that many shared models have recently begun to adopt licenses that prohibit merging or external commercialization. This has been a disappointment, as it has prevented me from using some truly excellent models for merging. I would like to express my heartfelt gratitude to the model developers who have provided free licenses, allowing their high-quality models—products of considerable time and effort—to be used for merging. I’ll be back soon. I eagerly look forward to your performance tests across a wide range of areas, including ANIME, REALISM, ARTISTIC, 2.5D, 3D, and NSFW. As model developers, we only plant the seeds. It is ultimately you, the model users and artists, who cultivate them and bring forth the flowers and fruits. Thank you, as always. For those who wish to support my work with a small financial contribution, please consider using the links below. I am currently unable to secure employment and face an uncertain future regarding my livelihood. The spec grid(380.5 MB): v2.1 Re-merge and adjust v0.1 to 2.0 using new merging algorithm and formula. The spec grid(424.5 MB): v2.0 I'd like to thank everyone who helped me on the side. Without you guys, the release date would probably have been much later. Thank you so much! - I have written a custom script to converge the existing AlbedoBase XL models into one. Intricately aligning the row and column weights of all U-NET and CLIP blocks according to a unique formula of mine. - If you encounter a bug in image generation (if nothing is generated), please switch to CLIP SKIP 2 or modify the prompt slightly! There may be combinations of prompts that CLIP does not recognize. In that case, you can change the order of words, use different words, or, most simply, change the CLIP SKIP. I will gradually work on resolving these issues in the future like v1.3. The spec grid(403.5 MB): v1.3 - In order to illustrate the quality associated with the model's randomness, I standardized the seed value at '9' for all showcase images intended for sampling and proceeded with their immediate generation. - Especially with
Mga trigger word
all in one
photo
2d
3d
anime
game
photorealistic
cinematic
design
base
4,973 download · 361 like sa Civitai
SHA256
8A8EFA5AD281317D3656ECE3D4CA81542DDE55DEB2079B2B37B48F145355C935
ModelTrends.ai Model ID
#7875
I-flag ang nilalaman
Mga halimbawang render
Mga prompt at setting na ibinahagi ng mga gumawa ng mga render na ito sa Civitai. Pumili ng render para makita kung paano ito ginawa.
Mga setting
Sampler
DPM++ 2M Karras
Steps
30
Guidance
7
Seed
2922473249
Laki
512x912
Clip skip
2
Prompt
a hiding and grumpy sasquatch concealed by trees and shrubs is peeking out and taking a photo of the viewer with an antique camera, autumn, uhd, 8k, intense lighting, award winning masterpiece, extremely detailed, detailed background, cinematic, complex and multidimensional lighting, <lora:xl_more_art-full_v1:0.6>,
Negative prompt
worst quality, low quality, ugly, blurry, unaesthetic, dull colors, bad hands,
Mga setting
Sampler
DPM++ 2M SDE Karras
Steps
60
Guidance
10
Seed
2246873310
Laki
1024x1024
Clip skip
2
Prompt
<lora:add-detail-xl:2.0>, famous artwork (by julie baroh:1.4), (fractal art:1.0), fantasy style, seen here is the wondrous (amphibic:1.2) gross warplobber with its psorbified quizzleflarp and (sleek, streamlined features:1.2), it prefers to drezzle next to one of the colorful and frequently (erupting geysers:1.4) of the blampfchoddering exoplanet new grinflob, masterpiece, best quality, ultra detailed
Negative prompt
boring, unsharp, blurry, artist name, signature, text, watermark
Mga setting
Sampler
DPM++ 2M Karras
Steps
35
Guidance
7
Seed
1618075656
Laki
1024x1024
Clip skip
1
Prompt
old dumb terminal displaying the text "404"
Negative prompt
(worst quality) and (low quality) and (normal quality) and (bad anatomy) and (semi-realistic:1.2) and (illustration:1.2) and (drawing:1.2) and (anti airbrushing:1.2) and (fake:1.2) and (doll:1.2) and (CG:1.2) and (painting:1.2) and (sketch:1.2) and (portrait:1.2) and (anthro:1.2) and (watermark:1.4)
Mga setting
Sampler
DPM++ 2M Karras
Steps
40
Guidance
7
Seed
3596433652
Laki
1024x1024
Prompt
Birthday cake, chocolate cake , drawing style ,
Negative prompt
poor quality , medium quality ,
Mga setting
Sampler
DPM++ 2M Karras
Steps
50
Guidance
10
Seed
849418503
Laki
1024x1024
Clip skip
1
Prompt
Broken destroyed Freddie FazBear as a Horror movie Antagonist, bloody knife in the hand, red glowing eyes, unsettling ambience, smooth lighting, 16k, life-like, realistic textures, hyper-realistic, in a mc Donalds
Negative prompt
comic, cartoon, anime, illustration, drawing, extra limbs, extra hands, extra fingers, noise, film grain, blur, blurry, low Quality, bad Quality, penny wise
Mga setting
Sampler
Default
Steps
20
Guidance
7
Seed
3905562380
Laki
512x904
Prompt
dark silhouette of a eclipse against the abstract background of light,(full body:1.1), dark theme, shadow and soft light around, subsurface scattering, soft light, intricate details, natural texture, amazing play of light and shadow, 8K, hyperdetailed, colorful background, triadic, swirling smoke <lora:xl_more_art-full_v1:0.75>
Negative prompt
ugly, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, extra limbs, body out of frame, bad anatomy, blurred, watermark, grainy, signature, cut off, draft, closed eyes, text, logo
Mga setting
Sampler
DPM++ 2M SDE Karras
Steps
70
Guidance
4.1
Seed
2720769277
Laki
720x1280
Prompt
beautiful and perfect 8k uhd professional photograph, sharp focus, In a stunning fantasy world, a cute 20yo silver-haired girl has black devil horns and beautiful hands, 1girl and a mysterious 1giant wolf, beaming with joy, in bright natural light
Negative prompt
worst quality, unrealistic and low details, blurred, nekomimi
Mga setting
Sampler
DPM++ 2M SDE Karras
Steps
60
Guidance
10
Seed
3357674569
Laki
1024x1024
Clip skip
2
Prompt
<lora:add-detail-xl:2.0>, famous artwork (by steve prescott:1.1), detailed expressive eyes, fantasy style, deep in the crystalline caverns of planet gullible secundus roams a silicon-based life form, the long-tailed eyejib, shown here as it is emerging from its tunnel lair in the vibrant, gemstone-studded walls of the underground shnorbsabbler, this creature is covered in crystalline quibberflitz arranged in colorful fractal patterns, reflecting the iridescent glow of the bioluminescent fungi around it, one should watch out for its dangerous punglyflorbed tail, masterpiece, best quality, ultra detailed
Negative prompt
boring, unsharp, blurry, artist name, signature, text, watermark
Mga AI model para sa paggawa ng larawan, video at teksto
Ang albedo xl ay isang base model para sa pamilyang Stable Diffusion XL 1.0 na nakalista sa ModelTrends.ai, isang read-only na catalog ng mga open source AI model para sa larawan, video at teksto. Ikumpara ito sa ibang Stable Diffusion XL 1.0 model, tingnan ang heat score nito para makita kung gaano ito kasikat, at buksan ito sa PirateDiffusion o BitVector para subukan.
Mag-browse ayon sa pamilya ng model
I-browse ang lahat ng model