Update README.md

README.md

@@ -1,7 +1,5 @@
 ---
 license: apache-2.0
-datasets:
-- peteromallet/high-quality-midjouney-srefs
 base_model:
 - Qwen/Qwen-Image-Edit
 tags:
@@ -18,7 +16,7 @@ library_name: diffusers
 
 ## Model Description
 
-**InScene** and **InScene Annotate** are a pair of LoRA fine-tunes for QwenEdit that enhance its ability to generate images based on scene references. These models work together to provide flexible scene-based image generation with optional annotation support.
+**InScene** and **InScene Annotate** are a pair of LoRA fine-tunes for QwenEdit that enhance its ability to generate images based on scene references. These models work together to provide flexible scene-based image generation with optional annotation support. **Both models are currently in beta and will be improved significantly over time.**
 
 ### InScene
 The main model that generates images based on scene composition and layout from a reference image. InScene is trained on pairs of different shots within the same scene, along with prompts describing the desired output. Its goal is to create entirely new shots within a scene while maintaining character consistency and scene coherence.
@@ -39,20 +37,21 @@ InScene Annotate is trained on images with green rectangles drawn over specific
 ### InScene
 To use the base InScene model, start your prompt with:
 
-`Make an image in this scene of `
+`Show a different image in the same scene of: `
 
 And then describe what you want to generate.
 
 For example:
-`Make an image in this scene of a bustling city street at night.`
+`Show a different image in the same scene of: a bustling city street at night.`
 
 ### InScene Annotate
-For the annotate variant, use annotated reference images and start your prompt with:
+To use InScene Annotate:
 
-`Based on this annotated scene, create `
+1. Draw a green rectangle over the subject or area of interest in your reference image
+2. Describe what you want to focus on and how it should change
 
 For example:
-`Based on this annotated scene, create a winter landscape with snow-covered mountains.`
+`Zoom in on the girl, make her turn to the side and laugh`
 
 ### Use with diffusers
 
@@ -95,12 +94,10 @@ The models may struggle with:
 
 ## Training Data
 
-The InScene and InScene Annotate LoRAs were trained on a curated dataset of high-quality Midjourney style references, with additional scene-focused annotations for the Annotate variant. The dataset emphasizes diverse scene compositions and spatial relationships.
+The InScene and InScene Annotate LoRAs were trained on curated datasets focusing on scene composition and spatial relationships. InScene uses pairs of different shots within the same scene, while InScene Annotate uses annotated images with green rectangle markers.
 
-You can find the public dataset used for training here:
-[https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs](https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs)
+The training data will be released publicly when it's in a more stable state.
 
 ## Links
 
-- Model: [https://huggingface.co/peteromallet/Qwen-Image-Edit-InScene](https://huggingface.co/peteromallet/Qwen-Image-Edit-InScene)
-- Dataset: [https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs](https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs)
+- Model: [https://huggingface.co/peteromallet/Qwen-Image-Edit-InScene](https://huggingface.co/peteromallet/Qwen-Image-Edit-InScene)