Card: v2 trained on Turbo, the original on RAW

README.md

@@ -137,10 +137,12 @@ Import it into Inline Studio, swap the reference images, and run the graph. It e
 character, compiles the FLUX.2 references, builds a training dataset from the same references,
 trains the Krea 2 LoRA, attaches it, and writes the `.char`.
 
-## Links
+## Related Workflows
 
-- [Inline Studio](https://github.com/inlineresearch/Inline-Studio): the node canvas and UI
-- [How to train](https://inlinestudio.art/workflows/flux-2-krea-2-multi-model-portable-consistent-characters-training-only)
+- [Flux 2: Portable consistent characters, without LoRA training](https://inlinestudio.art/workflows/flux-2-portable-consistent-characters-without-lora-training)
+- [Flux 2 + Krea 2: Multi model portable consistent characters, Training only](https://inlinestudio.art/workflows/flux-2-krea-2-multi-model-portable-consistent-characters-training-only)
+- [Krea 2: Generate consistent images with unified .char model](https://inlinestudio.art/workflows/krea-2-generate-consistent-images-with-unified-char-model)
+- [Flux 2 Klein: Generate consistent images with unified .char model](https://inlinestudio.art/workflows/flux-2-klein-generate-consistent-images-with-unified-char-model)
 
 ## License