update todo/changelog

Signed-off-by: vladmandic <mandic00@live.com>

CHANGELOG.md

@@ -10,7 +10,7 @@
     includes *Normal*, *Edit*, and *Lite* (distilled) variants  
     features lightweight SmolLM3-3B text encoder with efficient inference  
     *note*: this is a [gated model](https://vladmandic.github.io/sdnext-docs/Gated/)  
-    *note*: requires strict JSON prompts, not simple text (automatic prompt-to-json is future item)
+    *note*: requires verbose JSON prompts, simple text prompt suboptimial  
   - [AiArtLab SDXS-1B](https://huggingface.co/AiArtLab/sdxs-1b) Simple Diffusion XS *(training still in progress)*  
     this model combines Qwen3.5-1.8B text encoder with SDXL-style UNET with only 1.6B parameters and custom 32ch VAE  
     *note*: more of an experimental model and doesn't support offloading  

TODO.md

@@ -19,7 +19,6 @@
 - Feature: Multi-user support
 - Feature: Settings profile manager
 - Feature: Video tab add full API support
-- Feature: FIBO-Edit implement prompt-to-json
 - Refactor: Unify *huggingface* and *diffusers* model folders
 - Refactor: [GGUF](https://huggingface.co/docs/diffusers/main/en/quantization/gguf)
 - Reimplement `llama` remover for Kanvas

pipelines/bria/prompt_to_json.py

@@ -50,5 +50,5 @@ def before_prompt_encode(prompt):
     # dct = generate_prompt_local(prompt)
     # return dct
 
-    json_str = f'{{ "instructions": "{prompt}" }}'
+    json_str = '{ instructions: "' + prompt + '" }'
     return json_str