Model
Trends
.ai
Model
Trends
.ai
die besten Open-Source-KI-Modelle
Lokal ausführen
albedobaseXL_v20.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads werden von Civitai bereitgestellt. Manche Ersteller verlangen zuerst eine Anmeldung bei Civitai.
AD
Auf Graydient installieren / ausführen
Mitgliedschaft erforderlich
<albedo2-xl>
Über dieses Modell
STABLE DIFFUSION XL 1.0 · Basismodelle
Erstellt von
albedobond
auf Civitai
Notizen des Erstellers
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
21,325 Downloads · 1,489 Likes auf Civitai
SHA256
A928FEE35B39103CDF87A5059CAE6BAD66B30DE2CC17F739E1C3B8D88181C22B
ModelTrends.ai-Modell-ID
#8657
Inhalt melden
Beispielbilder
Prompts und Einstellungen, geteilt von den Leuten, die diese Bilder auf Civitai erstellt haben. Wähle ein Bild, um zu sehen, wie es entstanden ist.
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
50
Guidance
8
Seed
1067831013649047
Größe
416x608
Prompt
night female relaxed backlit (Deep Focus) contrast (f_stop 2.8), (focal_length 35.0) f/2.8, 35mm focal length Photograph of (view from above:1.42),analog photo,silhouette,spotlight,upper body view showing her face and (gigantic cleavage:1.15), a beautiful busty european woman,pale skin,highly detailed face, ultra detailed oiled sweaty dirty skin, dirty natural red hair, blue piercing eyes, eyes squinted, (lustful facial expression, lusty, lascivious:1.3), 1950s,dark background,warm colors, RAW candid cinema,16mm,color graded portra 400 film,remarkable color,ultra realistic,, captured on a (Fujifilm X-Pro3) / (f_stop 16.0), (focal_length 24.0)
Negativer Prompt
day, male, excited, frontlit, (Deep Focus) / (f_stop 1.8), (focal_length 85), brightness, (f_stop 1.2), (focal_length 14.0), viewfinder, digital look, modern images, (CyberRealistic_Negative-neg:0.8),mature,(deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime, mutated hands and fingers:1.4),(deformed, distorted, disfigured:1.3),poorly drawn,bad anatomy,wrong anatomy,extra limb,missing limb,floating limbs,disconnected limbs,mutation,mutated,ugly,amputation,tattoo,bruise,scar,open mouth,Asian-Less-Neg,child, kid,
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
30
Guidance
7
Seed
1504388572
Größe
768x1152
Prompt
by wlop and Ted Nasmith in the style of Božidar Jakac , radiant, mystical <lora:more_art:0.30><lora:clothing_slider:2.00><lora:great_lighting:1.30><lora:aesthetic:1.15><lora:photorealistic_portrait:1.25><lora:RMSDXL_Enhance:0.45><lora:RMSDXL_Creative:0.35><lora:RMSDXL_Photo:0.45><lora:RMSDXL_Darkness_Cinema:0.50><lora:XDetail_heavy:0.45><lora:perfect_eyes:0.15><lora:perfect_hands:0.15><lora:midjourney:-0.15><lora:looking_at_viewer:0.75><lora:dpo:0.25>
Negativer Prompt
low quality, bad anatomy, mess, bizarre, cartoon, painting, illustration, deviant
Einstellungen
Sampler
dpmpp_3m_sde_karras
Schritte
150
Seed
532514319835036
Größe
1624x2160
Prompt
(Illustration by Lee Jeffries), masterpiece:1.20, simple watercolor:1.5, uhd, hdr, 8k, unreal engine 5, ray tracing:1.20, low light painting, dramatic cinematic lighting, vibrant colors, vivid colors, Award-winning facial portrait of young Tinkerbell, (only face and upper body:1.3), (close up:1.2), (daintly young girl:1.30), wearing a loose delicate dress:1.2, single hair bun, looking down sideways, head tilt, (snub nose:1.3, red cheeks:1.20), prominent cheekbones, joyful smile:1.40, glossy skin:1.40 Spiritual illustration of a fairy village, inside a tree house with one big window, office, books, shelfes, candles, fairy dust, god rays,
Negativer Prompt
low resolution, low quality, cropped, bokeh, deformed finger, deformed hand, blurred eyes, deformed eyes, blurred eye pupils, incorrect anatomy, unnatural deformities, disfigured, unnatural mutations, bad anatomy, bad legs, bad feet, deformed limbs, extra limbs, missing limbs, floating limbs, separated limbs, disappearing arms, disappearing legs, long neck, abnormal legs, abnormal feet, abnormal fingers, overweight:1.4, intense makeup, heavy makeup, bad drawing, text, watermark, full body
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
30
Guidance
7
Seed
2092066022
Größe
832x1216
Clip skip
4
Prompt
LEGO style, lush exotic forrest, with a crystal clear water river flowing thru the middle, fluffy white cloud, sun flare, blue skies, highest quality, highest resolution, 8k UHD, HDR
Einstellungen
Sampler
Euler a
Schritte
15
Guidance
5
Seed
3443987040
Größe
960x1280
Clip skip
2
Prompt
Rabbit, <lora:FireBreath:0.7> breathing fire, open mouth, outdoors, fur
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
25
Guidance
3
Seed
206399677
Größe
1024x1280
Clip skip
2
Prompt
letitflrsh, let it flourish, Wobble-noodle, radiation, flowers, illumination, atmospheric, scale, order, healing, light, hope, soothing, calm, <lora:- SDXL - letitflrsh_let_it_flourish_V1.0:.8>
Negativer Prompt
nsfw, (symmetrical:1.2)
Einstellungen
Sampler
DPM++ 2M Karras
Schritte
30
Guidance
6
Seed
561108198
Größe
1024x1024
Clip skip
2
Prompt
Homeless man with laptop begging at a red light with a cardboard sign that reads "will train models for food"
Negativer Prompt
cartoon, drawing
Einstellungen
Sampler
DPM++ 2M
Schritte
30
Guidance
7
Seed
372736638
Größe
832x1216
Clip skip
2
Prompt
(Cute fluffy cow sleeping peacefully in a flower field), art by atey ghailan, painterly anime style at pixiv, art by kantoku, in art style of redjuice/necmi/rella/tiv pixiv collab, your name anime art style, masterpiece digital painting, exquisite lighting and composition, inspired by wlop art style, 8k, sharp, very detailed, high resolution, illustration
KI-Modelle für Bild-, Video- und Texterzeugung
albedo2 xl ist ein Basismodell für die Familie Stable Diffusion XL 1.0 und wird auf ModelTrends.ai gelistet, einem reinen Lesekatalog für Open-Source-KI-Modelle für Bild, Video und Text. Vergleiche es mit anderen Stable Diffusion XL 1.0-Modellen, prüfe den Hitzewert, um den Trend zu sehen, und öffne es auf PirateDiffusion oder BitVector, um es auszuprobieren.
Nach Modellfamilie stöbern
Alle Modelle ansehen