Upload 2 files
Browse files
photorealism/RealisticSnapShotz-Image-TurboV3.5.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd679d15ba836077264ccd9d7137166d626577fa6ce64a982077627ee22d954f
|
| 3 |
+
size 170127768
|
photorealism/readme.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Recommended Weight: 0.6 - 0.8 (V3 and v3.5 is more flexible and can handle higher weights, while V2 may require lower weights to tame instability.)
|
| 2 |
+
|
| 3 |
+
Trigger Words: While not strictly required, using these tags will force the model to activate specific textures and lighting styles:
|
| 4 |
+
|
| 5 |
+
For the "Camera Roll" Look: amateur digital snapshot, candid, smartphone capture, high ISO noise, direct on-camera flash
|
| 6 |
+
|
| 7 |
+
For High-Fidelity Details: visible pores, visible vellus hair, subsurface scattering, detailed skin texture (recommended to include at least one of these in every prompt)
|
| 8 |
+
|
| 9 |
+
For Lighting: hard flash, natural lighting, dimly lit, specular highlights
|
| 10 |
+
|
| 11 |
+
Prompting Strategy: Try combining the amateur aesthetic with high-quality subjects.
|
| 12 |
+
|
| 13 |
+
Example: amateur digital snapshot, candid, young woman, visible pores, vellus hair, flash photography, night time, outdoors
|