
Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
đ Join on Whop
đŹ Join the community for support, free tools and early news on Discord
This is the model you reach for when you want super clean, photo-realistic results.
Itâs sharp, powerful, and somehow just nails gorgeous images every single time.
âď¸ Recommended Settings
Sampling method: DPM++ 2M SDE Karras
VAE: is already Baked In
Sampling steps: 30+ Steps
Resolution: 832x1216 / 896x1152
CFG: 3-5
Clip Skip: 1
Upscale: 1.5 upscale (0.3 - 0.35 denoise)
Upscalers: 4x_NickelbackFS_72000_G / 4x_foolhardy_Remacri / 4x_NMKD-Siax_200kâď¸ Recommended Settings DMD2
Sampler: LCM
Schedule Type: Exponential
Sampling Steps: 8/12 (12 for extra detail)
CFG Scale: 1-1.5
⥠These settings are not the same as the standard SDXL workflow â be sure to adjust your pipeline!đĄ Whatâs the difference between FP16 and FP32 checkpoints?
FP16 (half precision) uses 16-bit floating-point weights. Itâs smaller in size, loads faster, and uses less VRAM - perfect for normal image generation. You wonât notice any visual difference for inference, so itâs ideal for everyday use.
FP32 (full precision) uses 32-bit weights, which means itâs larger and heavier on resources. It doesnât improve generation quality, but itâs better if youâre training, merging, or fine-tuning models, since it keeps the exact weight data without rounding loss.
đ§ Prompting
Example negative prompt:
cartoon, illustration, anime, painting, CGI, 3D render, low quality, watermark, logo, labelor use CyberRealistic Negative
⨠Optional Adetailer
Adetailer model: face_yolov9c.pt
If you only want the main face being refined set 'Mask only the top k largest' to 1.đ Links
Backup location: HuggingFace
â Fuel the Project
If this model gave you stellar results, consider buying me a coffee. Or two. Or, you know⌠a GPU.
â ď¸ Heads-Up
This model can make mature or sensitive content. Youâre fully responsible for what you create, so use it responsibly (or if you canât resist, at least be artistically irresponsible).
đŹ Want Better Prompts?
Use this custom ChatGPT to auto-generate polished prompts for CyberRealistic XL:
đ [Try it now on ChatGPT]
Description
Some slight enhancements in hands etc. (though not flawless), along with various other minor and more significant improvements.
FAQ
Comments (30)
Excellent
Model download hash mismatch, CivitAI gave E9337AE032D6 but download gave E9337AE032D6A2D411702FC6ACAD76BFBDDDEB1A697A62BFDB83881E949532C8.
Any ideas?
I've seen on Discord that there's a bug, and they're working on fixing it.
"SHA256 hashes fix incoming, models uploaded this morning with the short/invalid SHA256 will be rescanned."
@Cyberdelia thanks for the reply!
well done moving to SDXL. SDXL is better than stable cascade and anything else in my opinion, since there are more LORAS to SDXL, and 1024p is enough for any kind of upscaling. Perhaps try a "SDXL Lightning" version next? (sampler:euler&scheduler:sgm_uniform, cfg:1, 4steps)
I put so much hours in Cyberrealistic SD15 that it is difficult to move away from it. So personally I use SD15 Cyberrealistic most of the time. Still try to support/update it.
@Cyberdelia yeah, i know what you mean. Sometimes its simply not worth switching up to a new base-model. What do you think about SD3?
this makes no sense... I keep switching back to this model... What makes it so good above the mainstream? cfg high values?
Made with love ;)
Hello! I really love this model, it's one of the best I've tried for SDXL so far. Would it be possible for you to share an unpruned version so I could train my Loras using this? Much appreciated!
I would ever train LoRAS on the base SDXL model.
@Silmas Correct
@Silmas I like to experiment. I've had very good results training on models other than the base model. But thank you :)
@cassiebug1988Â sure you can have good results, but this LoRA is maybe not usable for other models then. That is why I always train the LoRAs for the base model.
@Silmas totally understandable, but personally as I only really use a few models anyway, I like to train on the model I plan on using with the lora. I have made plenty with the base model too that I like!
@cassiebug1988Â I have the unpruned version (hopefully), will try to upload it on huggingface. Don't know when - I need to search my backup drive which is not here.
@Cyberdelia I appreciate that so much! No worries if you can't, and no rush. thanks again!
I canât seem to use this in the on-site generator. Is that intentional or am I just dumb?
I really don't know.
It directs me to âuse on of my favorite generatorsâ like rundiffusion or seaart.ai. But I can use your older models to generate on Civitai. Maybe Civitai doesnât allow sdxl on-site generation yet?
Also, awesome work!!
major problems with limbs, fingers, legs
what's left...
@amazingbeauty suitcase
@amazingbeauty boobs
what's a better checkpoint in your opinion?
around a month ago i starting using comfyui, i'm still learning thingand now i wanted to try to do outpainting with sdxl on comfyui, i haven't got great result so far with the workflow i made or maybe the model/ setting i use, then i found your 1.5 model which seem to have a normal version and inpainting version, but for sdxl there only one version, so my question is can i use it ( this model the sdxl one) for outpainting or is outpainting in sdxl not working that great or need specific workflow or model to work ?
I gave up trying to find a good outpainting workflow in comfy. Everything i tried seems flawed in some way or other. In the end, started using fooocus as it does outpainting very well
This is my favorite checkpoint so far but it doesn't perform that well when it comes to hands and fingers.. Any suggestions?
got a suggestion for a checkpoint that does perform better in those areas?
Details
Files
cyberrealisticXL_v11VAE.safetensors
Mirrors
cyberrealisticXL_v11VAE.safetensors
CyberRealisticXLPlay_V1.1-VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors
cyberrealisticXL_v11VAE.safetensors













