Update README.md

README.md

@@ -53,12 +53,12 @@ It's tailored for especially for Ideogram 4 image-reference-prompt datasets, wit
 What we changed in AI-Toolkit besides the dataset editor:
 
 We added reference-latent token concatenation for Ideogram 4: each clean reference image is VAE-encoded and appended to the packed sequence as
-[text | noisy target | clean reference], with its own indicator, MRoPE time coordinate, and clean timestep. The transformer output and
+`[text | noisy target | clean reference]`, with its own indicator, MRoPE time coordinate, and clean timestep. The transformer output and
 diffusion loss are sliced to target tokens only, while bounding-box JSON prompts provide spatial edit conditioning.
 
 These changes have to be mirrored in ComfyUI as well:
 
-ComfyUI core: Extended the native Ideogram 4 model to accept reference latents and reproduce the training sequence [text | noisy output | clean reference],
+ComfyUI core: Extended the native Ideogram 4 model to accept reference latents and reproduce the training sequence `[text | noisy output | clean reference]`,
 including the separate indicator, MRoPE coordinate, clean timestep, and output-only prediction slicing.
 
 Custom node: Ideogram4ReferenceConditioning resizes and VAE-encodes a reference image to match the target latent, then attaches it only to positive