Update README.md

README.md

@@ -9,10 +9,12 @@ thumbnail: "https://huggingface.co/wavymulder/Analog-Diffusion-XL/resolve/main/i
 
 In your prompt, use the activation token: `analog style`
 
-Trained on *sd_xl_base_1.0_0.9vae.safetensors* 
+Sometimes pushes a green tint too hard, in these instances you can use negative prompting such as `green` or `split-toning` to help. Some prompts may struggle to generate consistently in color, in these instances you can use `sepia` and `grayscale` in negative to help.
 
 I typically use this LoRA at 0.6-1.0 Strength. All examples are generated on *sd_xl_base_1.0_0.9vae.safetensors* using this LoRA. No hi-res fix, upscaling, inpainting, etc. done on any samples here.
 
+Trained on *sd_xl_base_1.0_0.9vae.safetensors* 
+
 I have tested this LoRA with some popular community Photo SDXL checkpoints and gotten good results, you just may have to play around with the LoRA Strength to achieve your desired result (may need >1).
 
 Please see [this document where I share the parameters (prompt, sampler, seed, etc.) used for all example images.]( ADD LINK TO DOC HERE )