Fixed typos and formatting issues, and corrected the parameter count.

Fixed some typos and corrected formatting, as well as fixed the parameter account to 443.3M, there were also two places with conflicting parameter numbers, both of which were incorrect

README.md

@@ -16,7 +16,7 @@ language:
 # Aniimage-1
 
 Aniimage-1 is the first latent diffusion model developed by 8BitStudio.
-The model is a 256x256 anime image generation model trained from scratch using a UNet + VAE + CLIP architecture at 449.1 million parameters.
+The model is a 256x256 anime image generation model trained from scratch using a UNet + VAE + CLIP architecture at 433.37 million parameters.
 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.
 
 ## Model Details
@@ -25,12 +25,12 @@ Aniimage-1 has been trained on 830,001 anime images from [Danbooru](https://danb
 |---|---|
 | **Resolution** | 256×256 |
 | **Architecture** | Latent Diffusion (UNet + VAE + CLIP) |
-| **Parameters** | 441.9M |
+| **Parameters** | 433.37M |
 | **Training Steps** | 88,000 |
 | **Batch Size** | 64 |
 | **Dataset** | ~830K curated anime images from Danbooru |
 | **GPU** | NVIDIA RTX 5060 Ti 16GB |
-| **Scheduler** | DDIM or DPM ++ 2M |
+| **Scheduler** | DDIM or DPM++ 2M |
 
 ## Requirements
 
@@ -45,15 +45,15 @@ Aniimage-1 has been trained on 830,001 anime images from [Danbooru](https://danb
 
 [![Download Generator](https://img.shields.io/badge/Download-generate__hf.py-blue?style=for-the-badge)](https://huggingface.co/8BitStudio/Aniimage-1/resolve/main/generate_hf.py)
 
-after downloading, install the dependencies.
+After downloading, install the dependencies.
 
 ```bash
 pip install torch torchvision diffusers transformers safetensors pillow huggingface_hub
 python generate_hf.py
 ```
 
-recommended settings: Scheduler on DPM++ 2M with 25 steps and a CFG of 7.5. If you are using Euler, 30 steps and 5 CFG works the best.
-recommended negative prompt: "low quality, ugly, blurry, distorted, deformed, bad anatomy, bad proportions, extra limbs, missing limbs, watermark,
+Recommended settings: Scheduler on DPM++ 2M with 25 steps and a CFG of 7.5. If you are using Euler, 30 steps and 5 CFG works the best.
+Recommended negative prompt: "low quality, ugly, blurry, distorted, deformed, bad anatomy, bad proportions, extra limbs, missing limbs, watermark,
 text, signature, washed out, flat colors, manga panel, disfigured, poorly drawn, jpeg artifacts, cropped, out of frame"
 
 ## Prompting
@@ -78,7 +78,7 @@ Long prompts and enhanced prompts usually result in worse overall results. Try t
 
 - 256×256 resolution — fine details like hands and small features can be rough
 - Faces can sometimes look similar or 'melty' across different prompts
-- Little to none NSFW content — trained on mostly SFW dataset only
+- Little to no NSFW content — trained on mostly SFW dataset only
 - Does worse when generating men due to dataset bias
 
 
@@ -119,7 +119,7 @@ When using plain English text, you are much less likely to experience this issue
 
 **[Aniimage-2](https://huggingface.co/8BitStudio/Aniimage-2) is complete!**
 
-It features a native resolution of 512×512 and was trained on 1.2 million unique images, compared with the 830,000 images used to train Aniimage-1.
+It features a native resolution of 512×512 and was trained on 1.2 million unique images, compared with the 830,001 images used to train Aniimage-1.
 
 Aniimage-2 also switches from Aniimage-1’s epsilon-prediction objective to v-prediction and uses a zero-terminal signal-to-noise ratio. 
 It also uses uniform timestep sampling, while the upcoming Aniimage-3 will adopt logit-normal noise-level sampling as part of its flow-matching objective.