ExoCore XL/Pony
v4.5 Main | XL/Pony
Zyrnox
The main version of my ExoCore Merge Model, Fully Released. Feel free to publish anything made with this. This model does not require scores like pony and may make it worse if you do add the scores depending if you do "full body view," if you do, do full body view images might need a face detailer and some fixes.
The model can be found on CivitAI, SeaArt, PixAI.art and TensorArt.
I recommend, 2 - 7 CFG. 1 CFG is Hard to control but works, depending on how detailed the prompt and what not, I personally recommend 6 or 7. This Merge Model supports a wide range of LoRAs Both SDXL and Pony.
This merge is supposed to work with a lot of LoRAs so feel free to experiment.
What is ExoCore XL/Pony?
ExoCore XL/Pony is a highly specialized Image generation AI Model of type Safetensors / Checkpoint AI Model created by AI community user Zyrnox. Derived from the powerful Stable Diffusion (SDXL 1.0) model, ExoCore XL/Pony has undergone an extensive fine-tuning process, leveraging the power of a dataset consisting of images generated by other AI models or user-contributed data. This fine-tuning process ensures that ExoCore XL/Pony is capable of generating images that are highly relevant to the specific use-cases it was designed for, such as anime, style, illustration.
With a rating of 0 and over 0 ratings, ExoCore XL/Pony is a popular choice among users for generating high-quality images from text prompts.
Can I download ExoCore XL/Pony?
Yes! You can download the latest version of ExoCore XL/Pony from here.
How to use ExoCore XL/Pony?
To use ExoCore XL/Pony, download the model checkpoint file and set up an UI for running Stable Diffusion models (for example, AUTOMATIC1111). Then, provide the model with a detailed text prompt to generate an image. Experiment with different prompts and settings to achieve the desired results. If this sounds a bit complicated, check out our initial guide to Stable Diffusion – it might be of help. And if you really want to dive deep into AI image generation and understand how set up AUTOMATIC1111 to use Safetensors / Checkpoint AI Models like ExoCore XL/Pony, check out our crash course in AI image generation.
Popularity
Info
Version v4.5 Main | XL/Pony: 1 File
About this version: v4.5 Main | XL/Pony
Realized due to v4.0 that Anime is best for this overall, for everyone, including my self. Recommended for around 20 steps is a HiRes Fix, and Adetailer possibly.
# Stuff Merged In with V4.0 (Correct Order)
Voight Kampff (Checkpoint): 10% Clip, 10% Model
Prefect Pony XL V4.0 (Checkpoint): 3% Clip, 3% Model
ICBINP XL (Checkpoint): 2% Clip, 2% Model
FinitiCore Fusion V1.0 (Checkpoint): 30% Clip, 30% Model
Saved then Block Merged with V3, so it has the Style of V3. Once block merge was saved I then continued with the below:
Nova Furry Pony V6.0 (Checkpoint): 2%, Clip, 2% Model
RealLynxGirl style (LoRA): 3% Clip, 3% Model
Prefect Combo Merge V1.0 (Checkpoint): 4% Clip, 4% Model
Merged in with the first set of stuff at 4%, I know this makes it 4% a "incest" model, aka I merged it into itself once I added the three things mentioned.
# Cover Image Info (ComfyUI)
# Before HiRes Fix
Sampler: Euler A
Scheduler: Normal
Steps: 20
CFG: 6Resolution: 960 x 1280
Seed: 482984195462532
# HiRes Fix
Sampler: Euler A
Scheduler: Normal
Steps: 20
CFG: 6Seed: 886426023066334
# Prompts:
Positive Prompt: (masterpiece), best quality, A feral black wolf standing powerfully on a cliff edge, backlit by a huge, luminous full moon. The scene is set in a dark, rugged landscape under the moon's intense glow, with shadows cast dramatically across the cliff and the wolf’s fur. The atmosphere is moody and captivating, emphasizing the mystical connection between the wolf and the moon. Cinematic, high contrast, detailed lighting, natural lighting, howling, magic.
Negative Prompt: score_6, score_5, score_4, ugly, low quality, extra digits, jpeg artifacts, artifacts, extra fingers, four fingers, six fingers, seven fingers, missing finger, bad eyes, loli, shota, (extra ear, human ear), band hands, bad anatomy, extra horn, lowres, extra digit, fewer digits, cropped, worst quality, bad face, normal quality, signature, watermark, username, blurry, artist name, bad teeth, human ear, human ears, headband
10 Versions
Go ahead and upload yours!
