Update README.md

README.md

@@ -1,59 +1,80 @@
-# AnimeXL - Fine-Tuned Model on Anime Style Images  
+---
+license: other
+license_name: flux-1-dev-non-commercial-license
+license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
+language:
+  - en
+tags:
+  - flux
+  - diffusers
+  - lora
+  - replicate
+  - anime
+  - text-to-image
+base_model: black-forest-labs/FLUX.1-dev
+pipeline_tag: text-to-image
+instance_prompt: animexl
+widget:
+  - example_title: Futuristic Samurai
+    inputs:
+      prompt: animexl a cyberpunk samurai standing on a neon-lit rooftop, wearing black armor with glowing blue patterns, holding a katana with an electric blade, a bustling futuristic city in the background with flying cars and holographic billboards, cinematic lighting
+    outputs:
+      - image: https://example.com/samurai.png
+  - example_title: Magical Forest Scene
+    inputs:
+      prompt: animexl an ethereal elf princess with glowing silver hair, wearing a flowing emerald gown adorned with golden patterns, sitting by a glowing blue lake in an enchanted forest, surrounded by bioluminescent flowers, glowing fireflies, and ancient stone ruins covered in moss
+    outputs:
+      - image: https://example.com/forest.png
+---
 
-This LoRA (Low-Rank Adaptation) is fine-tuned using **200+ anime-style images** and trained over **2500 steps** to produce high-quality anime-style image generations. Use the trigger word **`animexl`** in your prompts for optimal results.  
+# AnimeXL - Fine-Tuned LoRA for Anime Image Generation
 
-## Features  
-- **Specialized for Anime Style:** Generates images with vibrant and detailed anime-style aesthetics.  
-- **Fine-tuned with 200+ Images:** Offers exceptional performance for anime-themed prompts.  
-- **Efficient and Flexible:** Works seamlessly with the 🧨 `diffusers` library.  
+AnimeXL is a LoRA fine-tuned using 200+ anime-style images over 2500 training steps. It specializes in creating vibrant, highly detailed anime-style visuals. The model leverages the **FLUX.1-dev** base model and is compatible with the 🧨 `diffusers` library for seamless integration.
 
 ---
 
-## How to Use  
-This LoRA is designed to be used with the **🧨 `diffusers` library** in Python. Below is an example to help you get started:
+## Features
+- **Trigger Word:** Use `animexl` in prompts to activate the model.
+- **High Compatibility:** Fully integrated with `diffusers` and works with FLUX.1-dev.
+- **Specialized Output:** Designed to generate anime-style artwork, perfect for creative projects.
 
-### Code Example  
+## How to Use
+
+### Using 🧨 Diffusers
 ```python
 from diffusers import AutoPipelineForText2Image
 import torch
 
-# Load the base model
+# Load the base pipeline
 pipeline = AutoPipelineForText2Image.from_pretrained(
-    'black-forest-labs/FLUX.1-dev', 
+    "black-forest-labs/FLUX.1-dev",
     torch_dtype=torch.float16
-).to('cuda')
+).to("cuda")
 
 # Load the LoRA weights
-pipeline.load_lora_weights('Nishit2411/AnimeXL', weight_name='lora.safetensors')
+pipeline.load_lora_weights("Nishit2411/AnimeXL", weight_name="lora.safetensors")
 
 # Generate an image
-prompt = "animexl a warrior in a futuristic city"
+prompt = "animexl a futuristic city with anime characters"
 image = pipeline(prompt).images[0]
 
 # Save or display the image
 image.save("output.png")
-```
-
----
-
-## Trigger Words  
-To achieve the best results, include **`animexl`** in your prompts. For example:  
-- `"animexl a magical girl in a serene forest"`  
-- `"animexl a futuristic city with anime characters"`  
-
----
-
-## Advanced Usage  
-For additional techniques like:  
-- **Weighting prompts**  
-- **Merging and fusing multiple LoRAs**  
-
-Refer to the official [diffusers documentation on loading LoRAs](https://huggingface.co/docs/diffusers/using-diffusers/lora).  
-
----
-
-## About AnimeXL  
-AnimeXL is a finely-tuned model created to enhance creativity and cater to anime-style generation enthusiasts. Developed using **Replicate's LoRA Trainer** at:  
-[LoRA Trainer](https://replicate.com/ostris/flux-dev-lora-trainer/train).  
 
-Let your imagination flow with AnimeXL! 🎨
+Trigger Words
+Use animexl in prompts to achieve optimal results. Example prompts:
+
+animexl a magical girl in a serene forest
+animexl a samurai standing under a cherry blossom tree at sunset
+About Training
+AnimeXL was trained on Replicate's LoRA Trainer using the following configuration:
+
+Base Model: FLUX.1-dev
+Training Steps: 2500
+Images: 200+ anime-style images
+Resolution: 512x512, 768x768, and 1024x1024
+Batch Size: 1
+Optimizer: AdamW8bit with a learning rate of 0.0004
+Scheduler: Flowmatch
+Sampling: Flowmatch with 28 steps, guidance scale of 3.5
+For more details, refer to Replicate's LoRA Trainer Documentation.