Quần Áo Bảo Hộ
1.0
Recommendations for using the Hyper model:Sampler = DPM SDE++ Karras or another / 4-6+ stepsCFG Scale = 1.5-2.0 (the lower the value, the more mutations, but the less contrast)
I also recommend using ADetailer for generation (some examples were generated with ADetailer, this will be noted in the image comments).
This model is available on Mage.Space (main sponsor).
You can also support me directly on Boosty.
Realistic Vision V6.0 (B2 - Full Re-train) Status (Updated: Apr. 4, 2024):
- Training Images: +3400 (B1: 3000)
- Training Steps: +724k (B1: 664k)
- Approximate percentage of completion: ~30%All models, including Realistic Vision (VAE / noVAE) are also on Hugging Face
ᅠ
Please read this! How to remove strong contrast.
To make the image less contrasty you can use LoRA [Detail Tweaker LoRA] in a negative value.
ᅠ
Orange Color = Optional
ᅠ
I use this template to get good generation results:
ᅠ
Prompt:
RAW photo, subject, 8k uhd, dslr, soft lighting, high quality, film grain, Fujifilm XT3
ᅠ
Negative Prompt:
- (deformed iris, deformed pupils, semi-realistic, cgi, 3d, render, sketch, cartoon, drawing, anime), text, cropped, out of frame, worst quality, low quality, jpeg artifacts, ugly, duplicate, morbid, mutilated, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, mutation, deformed, blurry, dehydrated, bad anatomy, bad proportions, extra limbs, cloned face, disfigured, gross proportions, malformed limbs, missing arms, missing legs, extra arms, extra legs, fused fingers, too many fingers, long neck, UnrealisticDream
- (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, disgusting, amputation, UnrealisticDream
ᅠ
Euler A or DPM++ SDE Karras
CFG Scale 3,5 - 7
Hires. fix with 4x-UltraSharp upscaler
Denoising strength 0.25-0.45
Upscale by 1.1-2.0
Clip Skip 1-2
ENSD 31337
ᅠ
Thanks to the creators of these models for their work. Without them it would not have been possible to create this model.
HassanBlend 1.5.1.2 by sdhassan
Uber Realistic Porn Merge (URPM) by saftle
Protogen x3.4 (Photorealism) + Protogen x5.3 (Photorealism) by darkstorm2150
Art & Eros (aEros) + RealEldenApocalypse by aine_captain
Dreamlike Photoreal 2.0 by sviasem
HASDX by bestjammer
Analog Diffusion by wavymulder
Life Like Diffusion by lutherjonna409
Analog Madness by CornmeisterNL
ICBINP - "I Can't Believe It's Not Photography" by residentchiefnz
The required VAE is already baked into the model.
This version (Code_1284) is a fix for many issues of 5.0 (artifacts, ugly faces, masculine female faces, small eyes, poor compatibility with LoRA and TI). In terms of realism this model may be worse than 5.0, but I tried to minimize losses.
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
The required VAE is already baked into the model.
This version (Code_1284) is a fix for many issues of 5.0 (artifacts, ugly faces, masculine female faces, small eyes, poor compatibility with LoRA and TI). In terms of realism this model may be worse than 5.0, but I tried to minimize losses.
- increased generation resolution to such resolutions as: 896x896, 768x1024, 640x1152, 1024x768, 1152x640. (note. in some cases there may still be mutations, duplications, etc -> will be fixed in future versions).
- improved sfw and nsfw for female and female anatomy (note. not all poses work correctly in such large resolutions -> will be fixed in future versions).
The required VAE is already baked into the model.
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
The required VAE is already baked into the model.
A custom VAE has been baked into the model.
This is the final version of the model. Wait for news about Realistic Vision based on SDXL.
Thanks to all who have used and are using my model, I appreciate you very much.
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
A custom VAE has been baked into the model.
This is the final version of the model. Wait for news about Realistic Vision based on SDXL.
Thanks to all who have used and are using my model, I appreciate you very much.
The necessary VAE is already baked into the model.
This version of the model focuses on photorealism and may be worse than version 2.0 in some aspects.
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
The necessary VAE is already baked into the model.
This version of the model focuses on photorealism and may be worse than version 2.0 in some aspects.
This model does not include VAE.
This version of the model focuses on photorealism and may be worse than version 2.0 in some aspects.
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
This model does not include VAE.
This version of the model focuses on photorealism and may be worse than version 2.0 in some aspects.
Recommended for use with VAE (to improve the quality of the generation and get rid of blue artifacts): https://huggingface.co/stabilityai/sd-vae-ft-mse-original
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
Recommended for use with VAE (to improve the quality of the generation and get rid of blue artifacts): https://huggingface.co/stabilityai/sd-vae-ft-mse-original
- vae-ft-mse-840000-ema-pruned.ckpt included
NOT FOR TRAINING!
Model for inpainting and outpainting.
Make sure that the model name has the ending -inpainting.
- vae-ft-mse-840000-ema-pruned.ckpt included
- vae-ft-mse-840000-ema-pruned.ckpt included