initial commit

.gitattributes

@@ -0,0 +1,55 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.lz4 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Audio files - uncompressed
+*.pcm filter=lfs diff=lfs merge=lfs -text
+*.sam filter=lfs diff=lfs merge=lfs -text
+*.raw filter=lfs diff=lfs merge=lfs -text
+# Audio files - compressed
+*.aac filter=lfs diff=lfs merge=lfs -text
+*.flac filter=lfs diff=lfs merge=lfs -text
+*.mp3 filter=lfs diff=lfs merge=lfs -text
+*.ogg filter=lfs diff=lfs merge=lfs -text
+*.wav filter=lfs diff=lfs merge=lfs -text
+# Image files - uncompressed
+*.bmp filter=lfs diff=lfs merge=lfs -text
+*.gif filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text
+*.tiff filter=lfs diff=lfs merge=lfs -text
+# Image files - compressed
+*.jpg filter=lfs diff=lfs merge=lfs -text
+*.jpeg filter=lfs diff=lfs merge=lfs -text
+*.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,184 @@
+---
+tags:
+- text-to-image
+- lora
+- diffusers
+- template:diffusion-lora
+widget:
+- output:
+    url: images/TryAnything_00204_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00205_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00144_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00145_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00158_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00159_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00154_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00155_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00148_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00149_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00128_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00129_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00124_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00125_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00122_.png
+  text: '-'
+- output:
+    url: images/TryAnything_00123_.png
+  text: '-'
+base_model: black-forest-labs/FLUX.1-Kontext-dev
+instance_prompt: try on this outfit, man try on this outfit, woman try on this outfit
+license: apache-2.0
+---
+# Try Anything
+
+<Gallery />
+
+## Model description 
+
+**Model Type:** LoRA  
+**Trained On:** Flux Kontext (via AI Toolkit)  
+**Best Results With:** Flux Kontext &#x2F; Flux Dev (untested but likely compatible)  
+**Trigger Word:** &#x60;try on this outfit&#x60;  
+**Purpose:** Virtual clothing try-on for realistic outfit visualization  
+
+**Workflow:** [Available on Patreon](https:&#x2F;&#x2F;www.patreon.com&#x2F;posts&#x2F;try-anything-134558142?utm_medium&#x3D;clipboard_copy&amp;utm_source&#x3D;copyLink&amp;utm_campaign&#x3D;postshare_creator&amp;utm_content&#x3D;join_link)
+
+---
+
+## 🧠 What is TryAnything?
+
+**TryAnything** is a virtual try-on LoRA designed to transfer clothing from product images onto people. It enables realistic visualization of how outfits would look on different individuals while preserving identity.
+
+The model was trained using **240 real-person images** from VTON datasets, focusing primarily on upper body garments with the ability to handle full outfit combinations.
+
+---
+
+## 🎯 What TryAnything Does
+
+TryAnything transfers clothing details including:
+
+- Upper body garments (shirts, blouses, jackets, tops)
+- Full outfit combinations (top + bottom)
+- Clothing fit and draping
+- Fabric textures and patterns
+- Natural clothing appearance on the target person
+
+---
+
+## 🧪 Training Info
+
+- **Trainer:** AI Toolkit
+- **Steps:** 6,000
+- **Dataset:** 240 real-person VTON images
+- **LoRA Rank:** 32
+- **Resolution:** 1024px
+- **Base Model:** Flux Kontext
+- **Focus:** Upper body garments with full outfit capability
+
+---
+
+## ⚙️ Usage Guide
+
+### **Recommended Settings:**
+- **LoRA Weight:** 1.0 (adjust as needed)
+- **Trigger:** &#x60;woman try on this outfit&#x60; or &#x60;man try on this outfit&#x60;
+- **Best Practice:** Use clothing images without people wearing them
+- **Can work:** With people wearing clothes, but not recommended
+
+### **Example Prompts:**
+&#x60;&#x60;&#x60;
+try on this outfit
+&#x60;&#x60;&#x60;
+&#x60;&#x60;&#x60;
+try on this outfit, man
+&#x60;&#x60;&#x60;
+&#x60;&#x60;&#x60;
+try on this outfit, man, copy t-shirt and shorts
+&#x60;&#x60;&#x60;
+&#x60;&#x60;&#x60;
+try on this outfit, blouse with short sleeves
+&#x60;&#x60;&#x60;
+
+---
+
+## ⚠️ Important Notes - Version 1 Limitations
+
+### **Current Limitations:**
+- **V1 Status:** This is the first version with room for improvement
+- **Head Proportions:** May have issues with head-to-body proportions (most common problem)
+- **Training Focus:** Primarily trained on upper body garments
+- **Bottom Wear:** Limited training on lower body clothing
+
+### **Best Results:**
+- Use standalone clothing images (not worn by people)
+- Specify clothing details in prompts when needed
+- Include &quot;anatomically correct proportions&quot; in prompts
+
+### **Future V2 Plans:**
+- Enhanced training with underwear and foundation garments
+- Improved lower body clothing handling
+- Better proportion consistency
+
+---
+
+## 📥 How to Use
+
+1. Load the LoRA in your workflow
+2. Use trigger: &#x60;woman try on this outfit&#x60; or &#x60;man try on this outfit&#x60;
+3. Provide clear clothing reference images (preferably unworn)
+4. Include clothing details in prompt if needed
+5. Add &quot;anatomically correct proportions&quot; for better results
+
+---
+
+## 🔬 Compatibility
+
+- **Primary:** Flux Kontext
+- **Likely Compatible:** Flux Dev (untested)
+- **Weight:** Start with 1.0, adjust up&#x2F;down as needed
+
+---
+
+**Feedback Welcome!** This is V1 - share your results and suggestions for improvements in V2!
+
+## Trigger words
+
+You should use `try on this outfit` to trigger the image generation.
+
+You should use `man try on this outfit` to trigger the image generation.
+
+You should use `woman try on this outfit` to trigger the image generation.
+
+
+## Download model
+
+
+[Download](/Alissonerdx/TryAnything/tree/main) them in the Files & versions tab.