Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Run Locally
sdxlHK_v097b.safetensors
6.46 GB · SafeTensor · fp16 · pruned
Downloads are served by Civitai. Some creators ask for a Civitai login first.
AD
Install / Run on Graydient
Requires membership
<cos97-xl>
About This Model
STABLE DIFFUSION XL 1.0 · Base Models
Created by
CN_Signal
on Civitai
Cosine-Continuous Stable Diffusion XL by Ciro Negrogni tries to fix tonality issues with SD models to produce the full color range from 'pitch black' to 'pure white', performing much better than noise offset or LoRA solutions. The focus is Cinematic, sci-fi, fashion, close-up photography, cyberpunk
Creator notes
V1.2 changelog: - improved consistency - new dataset trained V1.1 changelog: - train on 1.0 new dataset to integrate new linguistic depth and to add detail and precision - known issues: from version 1 onwards there are problems with hands and some anatomical parts. version 1.1 tries to fix some of these issues still present but less evident from v1 V1 changelog: training with large dataset and prompt from llm, accepts a t5xxl style as well as the usual tags best with : Deepshrink and Perturbed Attention Guidance unfortunately to alter the clip and model to integrate some sort of t5xxl made it more unstable and needs more control over the generation so I recommend using comfyui and take example from the nodes from my images V1 BETA2 changelog: - model completely redesigned from scratch - advanced training for fashion, photography and cinematic - merge DPO - beta features: lettering and magazine cover trigger for magazine cover : magazine cover trigger for trained covers:   SURFACE XIOX DIOR PAPER ID HERO GQ ADIDAS VIPER PORTER HARRODS LOVE WAN V INTERVIEW THE FACE TEENVOG HARPER'S BAZAAR ASOS WONDERLAND DAZED MIXMAG NUMERO WOMAN MOEVIR ALLURE WAD ROSALIA FASHION COSMOPOLITAN WALLPAPER BILLBOARD W L'OFFICEL GLAMOUR VOGUE FISHEYE ELLE TIME VOUGE PLAYBOY P.S.: preferably use karras or AYS as scheduler V0. 97b changelog: - Cinematic/sci-fi training 25 epochs 67000 steps - Fashion training 20 epochs 43000 steps - Detail + Unet training 10 epochs 70000 steps - + DPO merge CosXL versions : Cosine-Continuous Stable Diffusion XL is a new experimental SD model.  The most notable feature of this schedule is its capacity to fix tonality issues with SD models and  produce the full color range from 'pitch black' to 'pure white', performing much better than noise offset or LoRA solutions.  0.95c changelog: - more photographic, fix hands, fix eyes - close-up photography - better skin details - better raytracing - finetuned on new dataset 0.9 changelog: - more graphic (added 4 trained loRAs) - finetuned on best results of 0.75 0.75 changelog: - more sci-fi - more cyberpunk - more cinematic Introducing SDXL HK 0.9, the versatile amalgamation of cutting-edge advancements! This iteration pushes the boundaries of realism and sci-fi, evolving into a powerhouse of innovation. What's new in this version? Enhanced Graphics: We've amplified the visual experience by incorporating seven meticulously trained LoRAs, enriching the model's graphic capabilities to create more immersive content. Fine-tuning: Building on the success of the previous version (0.75) What set apart SDXL HK 0.75? Sci-Fi Infusion: Infusing more elements of science fiction, the model transcends traditional boundaries, weaving intricate and compelling narratives into its creations. Cyberpunk Vibe: Embracing the essence of cyberpunk, this version delivers a futuristic, edgy feel, opening doors to a plethora of creative possibilities. Cinematic: Elevating the cinematic experience, the model crafts visuals that resonate with cinematic grandeur, bringing stories to life in an immersive manner. Merged Model: SDXL HK 0.75 was built on a model by . Merges base, refiner, some LorRAs, and the model by Afroman4peace. Additionally, it underwent a second merge with two finely-tuned LoRA models specialized in photographic content. Maintaining Consistency: The primary goal behind this model's creation is to uphold a consistent quality standard alongside my LoRA models, ensuring coherence and reliability across various creative endeavors.
380 downloads · 34 likes on Civitai
SHA256
8CE6B152170FC49572BE72ED134D874CD94947929896FD5B80AEAEC72D326AF2
ModelTrends.ai Model ID
#2685
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++ 2M SDE Karras
Steps
30
Guidance
7
Seed
2832976258
Size
768x768
Clip skip
2
Prompt
noface, cyborg, close-up, neonbody, lightstreaks <lora:Neon_Cyberpunk_SDXL:0.8> <lora:Faceless_Cyborgs:0.8> (night:1.4), steam, depth of field, masterpiece, best quality, ultra high res, (photorealistic, realistic:1.2), deep shadow, raw photo,, raw photo, film grain, Fujifilm XT3, (photorealistic, realistic:1.2), deep shadow, 8k, uhd, dslr, ultra high res <lora:80s_punk_clothing:0.51> 80s punk clothing, Hyper-realistic, 16k resolution, intricate details. (masterpiece, award winning artwork) many details, extreme detailed, full of details, Wide range of colors, high Dynamic <lora:xl_more_art-full_v1:0.285> <lora:zavy-bcklt-sdxl:0.25> zavy-bcklt <lora:RMSDXL_Creative:0.24> <lora:add-detail-xl:1> <lora:MJ52:0.285>
Negative prompt
BeyondSDXLv4
Settings
Sampler
DPM++ 2M SDE Karras
Steps
30
Guidance
7
Seed
2565669321
Size
768x768
Clip skip
2
Prompt
noface, cyborg, close-up, neonbody, lightstreaks <lora:Neon_Cyberpunk_SDXL:0.8> (night:1.4), steam, depth of field, masterpiece, best quality, ultra high res, (photorealistic, realistic:1.2), deep shadow, raw photo,, raw photo, film grain, Fujifilm XT3, (photorealistic, realistic:1.2), deep shadow, 8k, uhd, dslr, ultra high res <lora:80s_punk_clothing:0.51> 80s punk clothing, Hyper-realistic, 16k resolution, intricate details. (masterpiece, award winning artwork) many details, extreme detailed, full of details, Wide range of colors, high Dynamic <lora:xl_more_art-full_v1:0.285> <lora:zavy-bcklt-sdxl:0.25> zavy-bcklt <lora:RMSDXL_Creative:0.24> <lora:add-detail-xl:1> <lora:MJ52:0.285>
Negative prompt
BeyondSDXLv4. signature, watermark
Settings
Sampler
dpmpp_2m_sde_gpu
Steps
60
Guidance
8
Seed
1101337822
Size
832x1216
Prompt
,… and white lines , style apollonmercedesaintclair , vector protest of woman hallmarkon the orchiin an optical illusion style . detailed j every unicef of takeoff . no obstrucourselves . the background is composed entirely by lines that create the illusion of depth cauley movement . a woman 's inviting figure , wonderfully perfect proportions gracefully embodies motion while being created from black vertical stripes , creating a captivating visual effect trance its mesmerizing and optical soi . this composition ostentatiously stema visually striking scene , drawing womenintech from wireless avarga , dakini , contemporary yoga such as cat cow , bridge , downward dog and puppy through graphic design
Negative prompt
photograph, photorealism, simplistic, minimalism, plain, simple, lonesome,
Settings
Sampler
DPM++ 2M SDE Karras
Steps
30
Guidance
7
Seed
3873603567
Size
768x768
Clip skip
2
Prompt
woman, cyberpunk, leather jacket, crowded bar, depth of field, neon light, platinum pixie cut, (blue eyes:1.2), light smile, (facing viewer:1.2), raw photo, film grain, Fujifilm XT3, (photorealistic, realistic:1.2), deep shadow, 8k, uhd, dslr, ultra high res <lora:CyberpunkMJXL:0.7> <lora:80s_punk_clothing:1> 80s punk clothing
Negative prompt
BeyondSDXLv4
Settings
Sampler
DPM++ 2M SDE Karras
Steps
30
Guidance
7
Seed
1935068512
Size
768x768
Clip skip
2
Prompt
woman, cyberpunk, leather jacket, crowded bar, depth of field, neon light, platinum pixie cut, (blue eyes:1.2), light smile, (facing viewer:1.2), raw photo, film grain, Fujifilm XT3, (photorealistic, realistic:1.2), deep shadow, 8k, uhd, dslr, ultra high res <lora:80s_punk_clothing:0.51> 80s punk clothing, Hyper-realistic, 16k resolution, intricate details. (masterpiece, award winning artwork) many details, extreme detailed, full of details, Wide range of colors, high Dynamic <lora:xl_more_art-full_v1:0.285> <lora:zavy-bcklt-sdxl:0.25> zavy-bcklt <lora:RMSDXL_Creative:0.24> <lora:add-detail-xl:1> <lora:MJ52:0.285>
Negative prompt
BeyondSDXLv4
Settings
Sampler
Euler a
Steps
20
Guidance
6
Seed
2232235853
Size
1000x1400
Prompt
score_9, score_8_up, score_7_up, <lora:Art_Deco_(Architecture)_(SDXL)_(AD):0.8> Art Deco, scenery, architecture, monumental architecture, building, city, cityscape, 8K, In'ei, chiaroscuro, rim lighting, perfect depth of field shot, beautiful, subsurface scattering, idealized city, wide beautiful boulevards, busy city center, parks and manicured lawn areas, large parks, plazas, detailed fluffy anime clouds, skyscrapers, made out of limestone, art deco windows, photographic realism, soft lighting, soft shading, art by Thomas Kinkade, BREAK zPDXL, zPDXLxxx, <lora:wowifierXL:0.2> art by mooncryptowow <lora:sdxl_lightning_8step_lora:0.4> <lora:detailed_notrigger:0.5>
Negative prompt
score_6_up, score_5_up, score_4_up, BREAK zPDXL-neg, zPDXLxxx-neg, negativeXL, NEG-fixl-2,(1), NEGATIVE_HANDS, signature, watermark, text, logo, underwear, disfigured face, pussy, vagina, boobs, female, women, extra limbs, blurry, slit, 2 sets of balls, extra hand, mutation, extra arms, legs in ground, body in ground, border, frame, 3 or more legs, 5 or more horns on the head area, bad hands, bad anatomy, copies, clones, twins, imperfect hands, deformed hands, human lips, human faces, humanoid faces, human nose, human, human mouth, hood, dog nose, cat nose, horns on head, falling feathers, floating feathers, misshapen windows, imperfect perspective, mutated buildings, gross building details, misaligned windows, circular windows, internal-organs-outside-the-body, internal-organs-visible, anatomy-description, unprompted-nsfw ,worst-human-external-anatomy, worst-human-hands-anatomy, worst-human-fingers-anatomy, worst-detailed-eyes, worst-detailed-fingers, worst-human-feet-anatomy, worst-human-toes-anatomy, worst-detailed-feet, worst-detailed-toes, camera, smartphone, worst-facial-details, ugly-detailed-fingers, ugly-detailed-toes,fingers-in-worst-possible-shape, worst-detailed-eyes, undetailed-eyes, undetailed-fingers, undetailed-toes,
AI Models for Image, Video & Text Generation
cos97 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