V1.2 changelog:<ul><li>improved consistency</li><li>new dataset trained</li></ul>V1.1 changelog:<ul><li>train on 1.0 new dataset to integrate new linguistic depth and to add detail and precision</li><li>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</li></ul>V1 changelog:training with large dataset and prompt from llm, accepts a t5xxl style as well as the usual tagsbest with : Deepshrink and Perturbed Attention Guidanceunfortunately 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 imagesV1 BETA2 changelog:<ul><li>model completely redesigned from scratch</li><li>advanced training for fashion, photography and cinematic</li><li>merge DPO</li><li>beta features: lettering and magazine covertrigger for magazine cover :magazine covertrigger for trained covers:  SURFACEXIOXDIORPAPERIDHEROGQADIDASVIPERPORTERHARRODSLOVE WANVINTERVIEWTHE FACETEENVOGHARPER'S BAZAARASOSWONDERLANDDAZEDMIXMAGNUMEROWOMANMOEVIRALLUREWADROSALIAFASHIONCOSMOPOLITANWALLPAPERBILLBOARDWL'OFFICELGLAMOURVOGUEFISHEYEELLETIMEVOUGEPLAYBOYP.S.: preferably use karras or AYS as scheduler</li></ul>V0. 97b changelog:<ul><li>Cinematic/sci-fi training 25 epochs 67000 steps</li><li>Fashion training 20 epochs 43000 steps</li><li>Detail + Unet training 10 epochs 70000 steps</li><li>+ DPO merge</li></ul>CosXL versions :<a target="_blank" rel="ugc" href="https://civarchive.com/models/400150?modelVersionId=446262">P2P EDIT VERSION</a>Cosine-Continuous Stable Diffusion XL is a new stability.ai 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:<ul><li>more photographic, fix hands, fix eyes</li><li>close-up photography</li><li>better skin details</li><li>better raytracing</li><li>finetuned on new dataset</li></ul>0.9 changelog:<ul><li>more graphic (added 4 trained loRAs)</li><li>finetuned on best results of 0.75</li></ul>0.75 changelog:<ul><li>more sci-fi</li><li>more cyberpunk</li><li>more cinematic</li></ul>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 <a target="_blank" rel="ugc" href="https://civarchive.com/models/119279/xl6-hephaistos-sd-10xl-sfwandnsfw">Afroman4peace</a>. 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.

SDXL HK

sdxlHK_v09LCM.safetensors

v0.9 LCM

v1.2

v1.1

v1.0

v1 BETA2

v0.97b COSXL

v0.97b

v0.97 COSXL

v0.95c COSXL

v0.95c TURBO

v0.95c

v0.9 TURBO

v0.9

v0.75

v0.6

Files with SHA256: f34aab8a0f29fa785c0d309e3de6477949cf3e027bf286274f8618c9113d517b