Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,40 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- image-to-image
|
| 4 |
+
- lora
|
| 5 |
+
- diffusers
|
| 6 |
+
- template:sd-lora
|
| 7 |
+
- ai-toolkit
|
| 8 |
+
- colorization
|
| 9 |
+
base_model: black-forest-labs/FLUX.1-Kontext-dev
|
| 10 |
+
instance_prompt: >-
|
| 11 |
+
colorize
|
| 12 |
+
license: unlicense
|
| 13 |
+
---
|
| 14 |
+
# COLORIZE TRUER (Variant 4)
|
| 15 |
+
## Low Rank Adapter (LoRA) for Flux Kontext
|
| 16 |
+
## Superior + Promptless Photo Colorization
|
| 17 |
+
## |||| By SilverAgePoets.com ||||
|
| 18 |
+
|
| 19 |
+
<Gallery />
|
| 20 |
+
|
| 21 |
+
Our aim with this checkpoint, & other Colorize Truer/+ LoRAs, is to help restore Kontext Dev towards the far more impressive photo colorization capabilities of Kontext Pro/Max, whilst further reinforcing task-specific reliability & realism at the standards of professional manual colorization. <br>
|
| 22 |
+
This checkpoint was merged from several of our trained variants using the sd-scripts [Flux LoRA merge script](https://github.com/kohya-ss/sd-scripts/blob/sd3/networks/flux_merge_lora.py). <br>
|
| 23 |
+
The constituent models were trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) over 500 grayscale/color pairings of real photos. <br>
|
| 24 |
+
|
| 25 |
+
The colorized (output) portion of our dataset consists of: <br>
|
| 26 |
+
Open use manual/professional colorizations of historic photos (roughly half of the data). <br>
|
| 27 |
+
Colorized outputs from Flux Kontext Max & Pro (the rest of the data). <br>
|
| 28 |
+
|
| 29 |
+
The source photos were sourced from public domain, and represent a broad scope of geographical, cultural, aesthetic, historical (from late 1830s thru today), & other contexts <br>.
|
| 30 |
+
|
| 31 |
+
## Trigger words
|
| 32 |
+
No trigger words neccessary. <br>
|
| 33 |
+
With that said, with some inputs, it may be neccessary to specify `colorize` or `colorize and upscale this photo. Leave all else the same.` as the instruction prompt. <br>
|
| 34 |
+
To "modernize" outputs, one may try: `Colorize and upscale the photo. Restore crisp detailing. Rich tonality. Make indistinguishable from top quality UHD 50MP+ or 12k+ pro 2025 DSLR camera colorized_02.CR2 photo. restore blurred details. Retain facial features with great fidelity source. Add fine detailing only where missing. Render real life like tones. Leave unchanged all else about photo.`, etc... <br>
|
| 35 |
+
|
| 36 |
+
## Further usage tips:
|
| 37 |
+
Make sure to match-up input/output dimensions, primarily to ensure fidelity of details/identity.
|
| 38 |
+
With starkly differing dimensions, the model might also get confused in regards to its instruction.
|
| 39 |
+
|
| 40 |
+
Out of our (already quite numerous) variants of this LoRA, this merged checkpoint has exhibited the most consistent results in our tests thus far.
|