Create README.md

README.md

@@ -0,0 +1,98 @@
+---
+license: cc0-1.0
+base_model:
+- Wan-AI/Wan2.2-T2V-A14B
+pipeline_tag: text-to-video
+tags:
+- lora
+- wan
+- text-to-video
+- object-typography
+- creative
+- artistic
+- text-to-image
+- diffusers
+- template:diffusion-lora
+widget:
+- text: >-
+    ObjectTypography. Aerial drone shot slowly revealing the word "GROW" formed by different stages of crop growth in agricultural fields. The 'G' is freshly plowed dark soil, 'R' is young green sprouts, 'O' is mature golden wheat, and 'W' is being harvested. The patchwork of fields creates a living timeline. Warm afternoon light, pastoral landscape.
+  output:
+    url: Videos/07229fd7-4606-4413-b9d4-14c3d651dba8.mp4
+- text: >-
+    ObjectTypography. Wide shot of an abandoned industrial warehouse where shafts of dusty sunlight streaming through broken roof panels spell "DECAY". Light beams cut through the darkness, particles floating in the illuminated air. Crumbling concrete and rusted machinery scattered throughout. Cinematic lighting, post-apocalyptic atmosphere, nature reclaiming man-made structures.
+  output:
+    url: Videos/10afd850-5c9d-4546-a4f8-bd1b019ab69a.mp4
+- text: >-
+    ObjectTypography. Bird's eye view of a skate park at dusk where skateboarders' chalk trails and scuff marks on black concrete spell "GRIND". The worn patterns from years of skating create weathered, organic letterforms. A few skaters are mid-trick, adding motion blur. Sodium vapor lights beginning to illuminate the scene. Urban, raw, authentic street culture aesthetic.
+  output:
+    url: Videos/3cfbe843-5a71-4220-9c03-ecb37621d1d6.mp4
+- text: >-
+    ObjectTypography. Neon signs in various colors flickering and buzzing to spell "GLOW" on a rain-soaked brick wall at night. Each letter is a different style of vintage neon - pink, cyan, yellow, and purple. Puddles on the ground reflect the luminous text. Steam rises from a nearby manhole. Shot in cyberpunk style with heavy grain and chromatic aberration.
+  output:
+    url: Videos/413c691a-7f5f-43fb-9a12-09267820b672.mp4
+- text: >-
+    ObjectTypography. High-angle shot of a massive junkyard where crushed and stacked vintage cars are arranged to spell "RUST" in towering letters. Each letter is 30 feet tall, constructed from oxidized metal in shades of orange, brown, and red. Overcast sky, industrial atmosphere, with a small figure welding at the base for scale. Cinematic composition.
+  output:
+    url: Videos/4494bbab-22e4-4950-b91e-878a1fb3a7c5.mp4
+- text: >-
+    ObjectTypography. Wide-angle shot of lightning strikes during a thunderstorm simultaneously forming the word "STRIKE" across a dark purple sky. Multiple bolts branch and fork to create the letters in a single moment. Silhouetted landscape below, rain visible as streaks. Dramatic storm clouds, electric energy, captured in that split-second of natural power. High-speed photography, raw elemental force.
+  output:
+    url: Videos/6fb6077e-854f-4091-98a9-bdf008d07c72.mp4
+---
+
+# **ObjectTypography LoRA for Wan**
+
+<Gallery />
+
+---
+
+> **Special Thanks:**  
+> This project was made possible thanks to generous sponsorship and GPU time provided by [reDMOND Ai](https://redmond.ai ).  
+> We are grateful for their support in training this LoRA.
+
+---
+
+## Model Description
+
+This LoRA specializes in creating ObjectTypography - a creative technique where words and letters are formed by natural and man-made objects in the environment. The model excels at spelling out words through clever arrangements of elements like crops, light, shadows, natural formations, and urban textures.
+
+This version is specifically adapted for use with **Wan-AI** models, like `Wan2.2-T2V-A14B`.
+
+## Trigger Words
+
+The trigger phrase is `ObjectTypography`.
+
+For best results, start your prompt with "ObjectTypography." followed by a description of how a word is formed by objects in a scene. The model will create dynamic, artistic compositions where letters emerge from environmental elements.
+
+## Setup for ComfyUI
+
+To use this LoRA in ComfyUI, simply place the file in your `loras` directory:
+
+-   Download `ObjectTypography-WAN22.safetensors` and place it in `ComfyUI/models/loras/`
+
+Ensure your ComfyUI environment is already configured to run Wan models.
+
+## Example Workflow (ComfyUI)
+
+In your ComfyUI workflow, add a **Load LoRA** node after your base model loader.
+
+1.  Load your base **Wan** model.
+2.  Connect the output of the model loader to the `model` input of the **Load LoRA** node.
+3.  Select `ObjectTypography-WAN22.safetensors` in the Load LoRA node.
+4.  Connect the `MODEL` output of the LoRA node to your KSampler.
+5.  Adjust the `strength_model` as needed (0.8-1.0 is a good starting point).
+
+### **References**
+-   **Base Model:** [Wan-AI/Wan2.2-T2V-A14B](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B)
+-   **ComfyUI:** [comfyanonymous/ComfyUI](https://github.com/comfyanonymous/ComfyUI )
+
+---
+### 🌐 Website
+You can find more of my models, projects, and information on my official website:
+- **[artificialguy.com](https://artificialguy.com/ )**
+
+### 💖 Support My Work
+If you find this model useful, please consider supporting my work. It helps me cover server costs and dedicate more time to new open-source projects.
+- **Patreon:** [Support on Patreon](https://www.patreon.com/user?u=81570187 )
+- **Ko-fi:** [Buy me a Ko-fi](https://ko-fi.com/artificialguybr )
+- **Buy Me a Coffee:** [Buy me a Coffee](https://buymeacoffee.com/jvkape )