Update README.md

README.md

@@ -1,3 +1,62 @@
----
-license: apache-2.0
----
+---
+tags:
+- image-to-image
+- lora
+- diffusers
+- template:sd-lora
+- ai-toolkit
+- colorization
+base_model: black-forest-labs/FLUX.1-Kontext-dev
+instance_prompt: >-
+   colorize
+license: unlicense
+widget:
+  - text: Colorize this photo (optional)
+    output:
+      url: outputs/01.png
+  - src: inputs/01.jpg
+    prompt: Colorize this photo (optional)
+    output:
+      url: outputs/01.png
+  - text: Colorize this photo (optional)
+    output:
+      url: outputs/02.png
+  - src: inputs/02.jpg
+    prompt: Colorize this photo (optional)
+    output:
+      url: outputs/02.png
+  - text: Colorize this photo (optional)
+    output:
+      url: outputs/03.png
+  - src: inputs/03.jpg
+    prompt: Colorize this photo (optional)
+    output:
+      url: outputs/03.png
+---
+# COLORIZE TRUER (Variant 6) 
+## Low(ish) Rank Adapter (LoRA) for Flux Kontext
+## Towards Consistent + Promptless Kontext Photo Colorization
+## |||| By SilverAgePoets.com ||||
+
+<Gallery />
+
+This version is from the same training as [Colorize Truer Var6](https://huggingface.co/AlekseyCalvin/ColorizeTruer_KontextFluxVar6_BySAP), but resized down from Rank 64 to Rank 16, for portability + easier merging with other variants. <br>
+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>
+This adapter was trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) over roughly 600 grayscale/colorized pairings of real archival photos. <br>
+
+The colorized (output) portion of the custom dataset we consolidated to train these "Colorize Truer" LoRAs consists of: <br>
+Open use manual/professional colorizations of historical photos (roughly half of the data). <br>
+Colorized outputs from Flux Kontext Max & Pro (the rest of the data). <br>
+
+The source photos were sourced from public domain, and represent a broad scope of geographical, cultural, aesthetic, historical (from late 1830s thru today), & other paradigms/contexts. <br>
+
+## Trigger words
+No trigger words neccessary. <br>
+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>
+One may also prompt in suggestions/corrections/directions, as far as specific choices of color. <br>
+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>
+
+## Further usage tips:
+For many inputs, a somewhat lower LoRA scale measure (0.7 or 0.8) seems to work best. Other inputs, however, seem to benefit from scales at around 1.2/1.3. <br>
+Make sure to match-up input/output dimensions, primarily to ensure fidelity of details/identity. <br>
+With starkly differing dimensions, the model might also get confused in regards to its instruction. <br>