icon-logo
Realities Edge XL Turbo 7
Checkpoint
coll-num126
look-num6407

V7

share
selectCommunity
Model Permissions:
prompt-imgEveryone Can See The Model
prompt-imgAnyone Can Use The Model
prompt-imgCommercial Use Permitted
S
SpectrumPsy
uploader
Details
Category
BASE MODEL
Type
Checkpoint-Trained
Base Model
SDXL 1.0
Support
ControlNet | I2I/T2I
Uploaded
March 13.2024
Added
126
Runs
6407
Security
Verified
Version Info
New V7 model turned TURBO - Fast but not as fast as Lightning! CFG 1-2 STEPS 4-8 DPM++ SDE or DPM++ 2M SDE More contrast? Higher CFG or steps!

⊣ Capabilities and recommendations:

  • Photorealism, 3D, 2.5D, Illustrations, Photomanipulation, Portraits and much more
  • NSFW capabilities
  • Works very well with Loras - both as a base to train on and for rendering
  • Excels at both types of CLIP prompting. Be it maximalist OpenAI style prompts or minimalist story driven LAION prompts (written in a more natural language without constant commas).
  • Great lighting and shines with easy short prompts and aggressive (but short) negative prompts.
  • Very low risk of burned generations even on higher CFG - recommend 5.5-15
  • Responds amazingly to hires.fix with just a scaling of 1.0-1.5 and beyond. I like doing it with no scaling at all, but just letting it run through with a sharp upscaler and less steps. If you have the VRAM for it, push the scaling higher, go nuts!
  • Favorite resolution ranges are 768x1344 and 1024x1296. Works good for landscapes on even bigger resolutions. Also works with anamorphic lenses in resolutions of 1920x816 or the likes. Test what works best for you.
  • DPM+ 3M SDE Karras recommended but always test your favorite!
  • All the img2img modes work really well and balancing a low CFG with a higher-than-average Denoising Strength will produce a sharp and clear upscale full of interesting details, using regular SD upscale. I wonder what you can do with Ultimate SD upscale?
  • Likes Clip Skip 1-4. I frequently use 2.
  • Knows about some celebrities - good LoRA base!
  • Use with ToMe (token merging) in A1111 (I'm sure it's implemented in Comfy as well) for a much faster SDXL generation time - changes seeds though!
Show More
Gallery
share
share