Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,57 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- Flux
|
| 5 |
+
- FluxPipeline
|
| 6 |
+
- text-to-image
|
| 7 |
+
- flux dev
|
| 8 |
+
- flux de-distilled
|
| 9 |
+
- image-generation
|
| 10 |
+
- flux-diffusers
|
| 11 |
+
- diffusers
|
| 12 |
+
- photo
|
| 13 |
+
- realism
|
| 14 |
+
pipeline_tag: text-to-image
|
| 15 |
+
library_name: diffusers
|
| 16 |
+
emoji: 🔜
|
| 17 |
+
language:
|
| 18 |
+
- en
|
| 19 |
+
base_model:
|
| 20 |
+
- black-forest-labs/FLUX.1-dev
|
| 21 |
+
|
| 22 |
+
---
|
| 23 |
+
|
| 24 |
+
**THIS MODEL WAS CREATED BY [SG161222 (aka "Evgeny")](https://huggingface.co/SG161222), the famed sole creator of milestone RealisticVision (on SD1.x) & RealVisXL (on SDXL) models.**
|
| 25 |
+
With those earlier series of fine-tuned modified base models, trained under severe resource limitations on consumer-level hardware, SG161222 had more than once revolutionized the photorealistic potentialities of open source text2image, single-handedly extending the horizons of the possible, raising the standards of the typical, and rendering far more accessible a lifelike quality once all-but elusive or restricted to arcane and unreliable recipes.
|
| 26 |
+
With this fresh series of models, created over the foundation of a de-destilled Flux.1 (and with a parallel S.D.3.5-based series now brewing), is SG161222 set to impact the generative sphere yet again, but at a more advanced technical baseline?
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
# Verus Vision — Model for Realistic Image Generation
|
| 30 |
+
|
| 31 |
+

|
| 32 |
+
|
| 33 |
+
# Overview
|
| 34 |
+
|
| 35 |
+
**Verus Vision** is a fine-tuned model designed for generating high-quality, realistic images. Built on the **Flux Dev (de-distill)** model with 12 billion parameters.
|
| 36 |
+
|
| 37 |
+
> ### You can support the creator, SD161222, directly on their <a href="https://boosty.to/sg_161222" style="color: #F15F2C"><b>Boosty</b></a>
|
| 38 |
+
|
| 39 |
+
<strong>Check out on the creator's exclusive models on Mage: </strong><a href="https://www.mage.space/play/4371756b27bf52e7a1146dc6fe2d969c" rel="noopener noreferrer nofollow"><strong>ParagonXL</strong></a><strong> / </strong><a href="https://www.mage.space/play/df67a9f27f19629a98cb0fb619d1949a" rel="noopener noreferrer nofollow"><strong>NovaXL</strong></a><strong> / </strong><a href="https://www.mage.space/play/d8db06ae964310acb4e090eec03984df" rel="noopener noreferrer nofollow"><strong>NovaXL Lightning</strong></a><strong> / </strong><a href="https://www.mage.space/play/541da1e10976ab82976a5cacc770a413" rel="noopener noreferrer nofollow"><strong>NovaXL V2</strong></a><strong> / </strong><a href="https://www.mage.space/play/a56d2680c464ef25b8c66df126b3f706" rel="noopener noreferrer nofollow"><strong>NovaXL Pony</strong></a><strong> / </strong><a href="https://www.mage.space/play/b0ab6733c3be2408c93523d57a605371" rel="noopener noreferrer nofollow"><strong>NovaXL Pony Lightning</strong></a><strong> / </strong><a href="https://www.mage.space/play/e3b01cd493ed86ed8e4708751b1c9165" rel="noopener noreferrer nofollow"><strong>RealDreamXL</strong></a><strong> / </strong><a href="https://www.mage.space/play/ef062fc389c3f8723002428290c1158c" rel="noopener noreferrer nofollow"><strong>RealDreamXL Lightning</strong></a></p>
|
| 40 |
+
|
| 41 |
+
<hr>
|
| 42 |
+
|
| 43 |
+
# How to Use Transformer Version
|
| 44 |
+
|
| 45 |
+
<hr>
|
| 46 |
+
# Optimal Generation Settings
|
| 47 |
+
* Sampling Method and Schedule Type: Euler Beta
|
| 48 |
+
* Sampling Steps: 25+
|
| 49 |
+
* CFG Scale: 3.5
|
| 50 |
+
|
| 51 |
+
> [!CREATOR'S WARNING]
|
| 52 |
+
> **Warning:** Do not use a negative prompt as it can lead to the generation of images with artifacts and distortions.
|
| 53 |
+
<hr>
|
| 54 |
+
# Limitations
|
| 55 |
+
* This version of the model does not have a variety of styles and is intended for realism and photorealism.
|
| 56 |
+
* There may be issues with anatomy and text.
|
| 57 |
+
|