Hugging Face's logo

8BitStudio
/
Aniimage-1

Text-to-Image
Diffusers
Safetensors
English
anime
diffusion
image-generation
Model card Files
xet
 Community
8BitStudio commited on
Commit
2af9df0
·
verified ·
1 Parent(s): fe32ade

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ language:
16
  # Aniimage-1
17
 
18
  Aniimage-1 is the first latent diffusion model developed by 8BitStudio.
19
- The model is a 256x256 anime image generation model trained from scratch using a UNet + VAE + CLIP architecture at around 400 million parameters.
20
  Aniimage-1 has been trained on 830,001 anime images from [Danbooru](https://danbooru.donmai.us/). It is not based on any existing models, the UNet is trained from scratch.
21
 
22
  ## Model Details
@@ -25,7 +25,7 @@ Aniimage-1 has been trained on 830,001 anime images from [Danbooru](https://danb
25
  |---|---|
26
  | **Resolution** | 256×256 |
27
  | **Architecture** | Latent Diffusion (UNet + VAE + CLIP) |
28
- | **Parameters** | ~400M |
29
  | **Training Steps** | 88,000 |
30
  | **Batch Size** | 64 |
31
  | **Dataset** | ~830K curated anime images from Danbooru |
 
16
  # Aniimage-1
17
 
18
  Aniimage-1 is the first latent diffusion model developed by 8BitStudio.
19
+ The model is a 256x256 anime image generation model trained from scratch using a UNet + VAE + CLIP architecture at 449.1 million parameters.
20
  Aniimage-1 has been trained on 830,001 anime images from [Danbooru](https://danbooru.donmai.us/). It is not based on any existing models, the UNet is trained from scratch.
21
 
22
  ## Model Details
 
25
  |---|---|
26
  | **Resolution** | 256×256 |
27
  | **Architecture** | Latent Diffusion (UNet + VAE + CLIP) |
28
+ | **Parameters** | 441.9M |
29
  | **Training Steps** | 88,000 |
30
  | **Batch Size** | 64 |
31
  | **Dataset** | ~830K curated anime images from Danbooru |