Hugging Face's logo

NewBie-AI
/
NewBie-image-Exp0.1

Text-to-Image
Diffusers
Safetensors
English
NewbiePipeline
next-dit
transformer
image-generation
Anime
Model card Files
xet
Community
2
E-Anlia commited on
Commit
53f2cfd
·
verified ·
1 Parent(s): e19a4e7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -26,7 +26,7 @@ base_model:
26
  [![GitHub - ComfyUI-NewBie](https://img.shields.io/badge/GitHub-ComfyUI--NewBie-181717?logo=github&logoColor=white)](https://github.com/NewBieAI-Lab/ComfyUI-Newbie-V0.1) 
27
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-NewBie%20image%20Exp0.1-yellow)](https://huggingface.co/NewBie-AI/NewBie-image-Exp0.1) 
28
  ![C5BDBA2F0B1D85D81D3A9DCADF6DED1F](https://cdn-uploads.huggingface.co/production/uploads/67fdc3911c5d7301352a0507/qB2wyVrTuYBtg_ToRb2wP.jpeg)
29
- </div>
30
  ## 🧱Exp0.1 Base
31
  **NewBie image Exp0.1** is a **3.5B** parameter DiT model developed through research on the Lumina architecture.
32
  Building on these insights, it adopts Next-DiT as the foundation to design a new NewBie architecture tailored for text-to-image generation.
@@ -36,7 +36,7 @@ We use Gemma3-4B-it as the primary text encoder (conditioning on its second-to-l
36
  Benefiting from Gemma3-4B-it and Jina CLIP v2, NewBie image Exp0.1 achieves strong prompt understanding and instruction-following capability.
37
  #### VAE
38
  Use the FLUX.1-dev 16channel VAE to encode images into latents, delivering richer, smoother color rendering and finer texture detail helping safeguard the stunning visual quality of NewBie image Exp0.1.
39
-
40
  ## 🖼️Task type
41
  **NewBie image Exp0.1** is pretrain on a large corpus of high-quality anime data, enabling the model to generate remarkably detailed and visually striking anime style images.
42
  ![NewBie image preview](https://huggingface.co/NewBie-AI/NewBie-image-Exp0.1/resolve/main/image/newbie_image.png)
 
26
  [![GitHub - ComfyUI-NewBie](https://img.shields.io/badge/GitHub-ComfyUI--NewBie-181717?logo=github&logoColor=white)](https://github.com/NewBieAI-Lab/ComfyUI-Newbie-V0.1)&#160;
27
  [![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Checkpoint-NewBie%20image%20Exp0.1-yellow)](https://huggingface.co/NewBie-AI/NewBie-image-Exp0.1)&#160;
28
  ![C5BDBA2F0B1D85D81D3A9DCADF6DED1F](https://cdn-uploads.huggingface.co/production/uploads/67fdc3911c5d7301352a0507/qB2wyVrTuYBtg_ToRb2wP.jpeg)
29
+
30
  ## 🧱Exp0.1 Base
31
  **NewBie image Exp0.1** is a **3.5B** parameter DiT model developed through research on the Lumina architecture.
32
  Building on these insights, it adopts Next-DiT as the foundation to design a new NewBie architecture tailored for text-to-image generation.
 
36
  Benefiting from Gemma3-4B-it and Jina CLIP v2, NewBie image Exp0.1 achieves strong prompt understanding and instruction-following capability.
37
  #### VAE
38
  Use the FLUX.1-dev 16channel VAE to encode images into latents, delivering richer, smoother color rendering and finer texture detail helping safeguard the stunning visual quality of NewBie image Exp0.1.
39
+ </div>
40
  ## 🖼️Task type
41
  **NewBie image Exp0.1** is pretrain on a large corpus of high-quality anime data, enabling the model to generate remarkably detailed and visually striking anime style images.
42
  ![NewBie image preview](https://huggingface.co/NewBie-AI/NewBie-image-Exp0.1/resolve/main/image/newbie_image.png)