Update README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,7 @@ language:
|
|
| 6 |
- en
|
| 7 |
- zh
|
| 8 |
---
|
| 9 |
-
|
| 10 |
-
# Model Card for VAR (Visual AutoRegressive) Transformers 🔥
|
| 11 |
|
| 12 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 13 |
|
|
@@ -15,7 +14,7 @@ language:
|
|
| 15 |
|
| 16 |
[](https://sites.google.com/view/minedreamer/main)
|
| 17 |
|
| 18 |
-
MineDreamer is an instructable embodied agent for simulated control and it is developed on top of recent advances in Multimodal Large Language Models (MLLMs) and diffusion models!
|
| 19 |
|
| 20 |
|
| 21 |
|
|
@@ -23,7 +22,7 @@ MineDreamer is an instructable embodied agent for simulated control and it is de
|
|
| 23 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/63f08dc79cf89c9ed1bb89cd/S62I1Tn5qz5qJ3IkgMHH8.png" width=93%>
|
| 24 |
<p>
|
| 25 |
|
| 26 |
-
MineDreamer can follow instructions steadily by employing a Chain-of-Imagination (CoI) mechanism to envision the step-by-step process of executing instructions and translating imaginations into more precise visual prompts tailored to the current state; subsequently, it generates keyboard-and-mouse actions to efficiently achieve these imaginations,
|
| 27 |
|
| 28 |
|
| 29 |
<p align="center">
|
|
@@ -31,6 +30,6 @@ MineDreamer can follow instructions steadily by employing a Chain-of-Imagination
|
|
| 31 |
<p>
|
| 32 |
|
| 33 |
|
| 34 |
-
**This repo is used for hosting MineDreamer's InstructPix2Pix checkpoints, which
|
| 35 |
|
| 36 |
For more details or tutorials see https://github.com/Zhoues/MineDreamer.
|
|
|
|
| 6 |
- en
|
| 7 |
- zh
|
| 8 |
---
|
| 9 |
+
# Model Card for *MineDreamer* 🔥
|
|
|
|
| 10 |
|
| 11 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 12 |
|
|
|
|
| 14 |
|
| 15 |
[](https://sites.google.com/view/minedreamer/main)
|
| 16 |
|
| 17 |
+
*MineDreamer* is an instructable embodied agent for simulated control and it is developed on top of recent advances in Multimodal Large Language Models (MLLMs) and diffusion models!
|
| 18 |
|
| 19 |
|
| 20 |
|
|
|
|
| 22 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/63f08dc79cf89c9ed1bb89cd/S62I1Tn5qz5qJ3IkgMHH8.png" width=93%>
|
| 23 |
<p>
|
| 24 |
|
| 25 |
+
*MineDreamer* can follow instructions steadily by employing a Chain-of-Imagination (CoI) mechanism to envision the step-by-step process of executing instructions and translating imaginations into more precise visual prompts tailored to the current state; subsequently, it generates keyboard-and-mouse actions to efficiently achieve these imaginations,
|
| 26 |
|
| 27 |
|
| 28 |
<p align="center">
|
|
|
|
| 30 |
<p>
|
| 31 |
|
| 32 |
|
| 33 |
+
**This repo is used for hosting MineDreamer's InstructPix2Pix checkpoints, which are not only the baseline checkpoints but the training stage 2 checkpoints for Imaginator as well.**
|
| 34 |
|
| 35 |
For more details or tutorials see https://github.com/Zhoues/MineDreamer.
|