Update README.md

README.md

@@ -1,80 +1,66 @@
 ---
-language: en
 license: mit
-library_name: diffusers
 tags:
-- flux
 - text-to-image
-- diffusers
 - lora
+- diffusers
+- template:sd-lora
 - education
 - childrens illustrations
-datasets:
-- comarproject/sida-handdraw-dataset
-base_model:
-- black-forest-labs/FLUX.1-dev
-pipeline_tag: text-to-image
----
-
-# Learn Isle HD 0.1
-
-## Model Description
-
-Learn Isle HD 0.1 is a LoRA (Low-Rank Adaptation) model fine-tuned on the FLUX.1-dev base model. It is specifically designed to generate hand-drawn style images for an upcoming educational game called "Learn Isle" targeted at children. This model was created by the inpocket.ai team for use in inpocket.games projects, featuring the distinctive hand-drawn style of artist Sida.
-
-## Intended Use
-
-This model is intended for generating consistent hand-drawn style images for the educational game "Learn Isle". It excels at creating illustrations of objects, people, and items in a child-friendly, educational context. The model is particularly effective when prompts begin with "hand drawn illustration of a [object/person/item etc.]".
-
-## Base Model
-
-This LoRA is based on the [FLUX.1-dev model](https://huggingface.co/black-forest-labs/FLUX.1-dev) by Black Forest Labs, which is a diffusion model similar to Stable Diffusion.
+- hand-drawn
+- flux
+base_model: black-forest-labs/FLUX.1-dev
+instance_prompt: hand drawn illustration
+widget:
+- text: 'hand drawn illustration of an alien with white background'
+  output:
+    url: sida-hd (1).png
+- text: 'hand drawn illustration of napoleon'
+  output:
+    url: sida-hd (10).png
 
-## Training Data
+---
 
-The model was trained on a custom dataset consisting of hand-drawn illustrations by artist Sida. These illustrations were specifically created for the "Learn Isle" educational game, ensuring a consistent and appropriate style for children's educational content.
+# Sida Hand Drawn 0.1 (sida-hd-01)
 
-## Training Procedure
+<Gallery />
 
-The model was trained using the following configuration:
+## Model description
 
-- **LoRA Rank**: 32
-- **Training Steps**: 3000
-- **Learning Rate**: 1e-4
-- **Batch Size**: 1
-- **Resolution**: [512, 768, 1024]
-- **Scheduler**: FlowMatch
-- **Optimizer**: AdamW8bit
-- **Precision**: bfloat16
+Sida Hand Drawn 0.1 (sida-hd-01) is a LoRA (Low-Rank Adaptation) model fine-tuned on the FLUX.1-dev base model. It is specifically designed to generate hand-drawn style images for an upcoming educational game called "Learn Isle" targeted at children. This model was created by the inpocket.ai team for use in inpocket.games projects, featuring the distinctive hand-drawn style of artist Sida.
 
-## Evaluation Results
+The model works best when you include 'hand drawn illustration of a' at the beginning of your prompt. It excels at creating illustrations of objects, people, and items in a child-friendly, educational context.
 
-The model's performance was evaluated throughout the training process with samples generated every 250 steps. These samples were used to assess the quality and style consistency of the generated images, ensuring they matched the desired hand-drawn aesthetic for the "Learn Isle" game.
+Training details:
+- LoRA Rank: 32
+- Training Steps: 3000
+- Learning Rate: 1e-4
+- Batch Size: 1
+- Resolution: [512, 768, 1024]
+- Scheduler: FlowMatch
+- Optimizer: AdamW8bit
+- Precision: bfloat16
 
-## Optimal Usage
+The model was trained on a custom dataset of hand-drawn illustrations by artist Sida, specifically created for the "Learn Isle" educational game.
 
-For best results, start your prompts with "hand drawn illustration of a [object/person/item etc.]". This prompt structure tends to produce the most consistent and desirable outputs in the intended style.
+## Trigger words
 
-## Limitations
+You should use `hand drawn illustration of a` at the beginning of your prompt to trigger the image generation in the intended style.
 
-- The model is specifically tailored for the "Learn Isle" game style and may not generalize well to other artistic styles.
-- It performs best with simple, child-friendly concepts and may struggle with complex or adult-themed prompts.
-- The hand-drawn style is consistent but limited to the artistic style of Sida, the artist whose work was used for training.
+## Download model
 
-## Ethical Considerations
-
-This model is designed for creating educational content for children. Users should ensure that generated content is appropriate, educational, and free from harmful or inappropriate elements. The model should not be used to generate content that could be misleading or detrimental to a child's learning experience.
+Weights for this model are available in Safetensors format.
 
-## Example Usage
+[Download](/inpocketai/sida-hd-01/tree/main) them in the Files & versions tab.
 
-To use this model with the Diffusers library:
+## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
 
-```python
+```py
 from diffusers import FluxPipeline, FluxLoraConfig
 import torch
 
 model_id = "black-forest-labs/FLUX.1-dev"
-lora_id = "comarproject/learn-isle-hd-0"
+lora_id = "inpocketai/sida-hd-01"
 
 pipe = FluxPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
 lora_config = FluxLoraConfig.from_pretrained(lora_id)
@@ -82,15 +68,22 @@ pipe.load_lora_weights(lora_id)
 
 prompt = "hand drawn illustration of a friendly robot teaching mathematics"
 image = pipe(prompt, num_inference_steps=20, guidance_scale=4.0).images[0]
-image.save("learn_isle_math_robot.png")
+image.save("sida_hd_math_robot.png")
 ```
 
+For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
+
+## Ethical Considerations
+
+This model is designed for creating educational content for children. Users should ensure that generated content is appropriate, educational, and free from harmful or inappropriate elements. The model should not be used to generate content that could be misleading or detrimental to a child's learning experience.
+
 ## Additional Information
 
-- **Developer**: inpocket.ai team for inpocket.games
-- **Version**: 0.1
-- **Date Created**: September 27, 2024
-- **License**: MIT
-- **Artist**: Sida
+- Developer: inpocket.ai team for inpocket.games
+- Version: 0.1
+- Date Created: September 27, 2024
+- License: MIT
+- Artist: Sida
+- HD: In the context of this model, HD stands for "Hand Drawn"
 
-For more information about Learn Isle, inpocket.ai, and inpocket.games, please visit our website or contact our team.
+For more information about Learn Isle, inpocket.ai, and inpocket.games, please visit our [website](https://www.inpocket.ai) or contact our team.