Update README.md

README.md

@@ -16,13 +16,8 @@ The LDM3D model was proposed in ["LDM3D: Latent Diffusion Model for 3D"](https:/
 
 LDM3D got accepted to [CVPRW'23]([https://aaai.org/Conferences/AAAI-23/](https://cvpr2023.thecvf.com/)).
 
-
-  
-These datasets were augmented using [Text2Light](https://frozenburning.github.io/projects/text2light/) to create a dataset containing 13852 training samples and 1606 validation samples.
-
-In order to generate the depth map of those samples, we used [DPT-large](https://github.com/isl-org/MiDaS) and to generate the caption we used [BLIP-2](https://huggingface.co/docs/transformers/main/model_doc/blip-2)
-
-A demo using this checkpoint has been open sourced in [this space](https://huggingface.co/spaces/Intel/ldm3d)
+This checkpoint has been finetuned on panoramic images (see how we finetuned below)
+A demo using this checkpoint has been open-sourced in [this space](https://huggingface.co/spaces/Intel/ldm3d)
 
 ## Model description
 
@@ -36,7 +31,7 @@ This research paper proposes a Latent Diffusion Model for 3D (LDM3D) that genera
 
 You can use this model to generate RGB and depth map given a text prompt.
 A short video summarizing the approach can be found at [this url](https://t.ly/tdi2) and a VR demo can be found [here](https://www.youtube.com/watch?v=3hbUo-hwAs0).
-
+A demo is also accessible on [Spaces](https://huggingface.co/spaces/Intel/ldm3d)
 
 ### How to use
 
@@ -63,16 +58,6 @@ This is the result:
 ![ldm3d_results](ldm3d_pano_results.png)
 
 
-### Limitations and bias
-
-For the image generation, limitations and bias are the same as the ones from [Stable diffusion](https://huggingface.co/CompVis/stable-diffusion-v1-4#limitations)
-For the depth map generation, a first limitiation is that we are using DPT-large to produce the ground truth, hence, other limitations and bias are the same as the ones from [DPT](https://huggingface.co/Intel/dpt-large).
-
-
-## Training data
-
-The LDM3D model was finetuned on a dataset constructed from a subset of the LAION-400M dataset, a large-scale image-caption dataset that contains over 400 million image-caption pairs.
-
 ### Finetuning
 
 This checkpoint finetunes the previous [ldm3d-4c](https://huggingface.co/Intel/ldm3d-4c) on 2 panoramic-images datasets: