Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,22 @@ saved_model/**/* 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
+48ecf48e-20a5-4f5f-8532-a9a8b4d838f0.png filter=lfs diff=lfs merge=lfs -text
+swappy-20260101-222728.png filter=lfs diff=lfs merge=lfs -text
+z-image_00164_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00168_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00172_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00176_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00182_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00242_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00252_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00256_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00260_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00268_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00272_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00276_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00286_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00292_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00296_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00301_.png filter=lfs diff=lfs merge=lfs -text
+z-image_00306_.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,169 @@
+---
+license: other
+library_name: diffusers
+tags:
+- text-to-image
+- lora
+- diffusers
+- z-image-turbo
+- anime
+base_model: Tongyi-MAI/Z-Image-Turbo
+---
+
+# Z-Image Turbo LoRA Guide (Best Version)
+
+![Cover Image](z-image_00306_.png)
+
+**Updated:** Jan 7, 2026  
+**Type:** LoRA  
+**Base Model:** ZImageTurbo  
+**Training:** Steps: 5,000 | Epochs: 42  
+**Trigger Word:** `aimaginedworlds`
+
+## The Best Result: V1 Adapter Training
+**Style:** Anime / Illustration  
+**Base Model:** Tongyi-MAI/Z-Image-Turbo
+
+## 📖 My Story: The Road to the "Perfect" LoRA
+I want to share my experience training this LoRA—not just the final product, but the entire journey, because I believe transparency helps the community learn.
+
+### 🚫 Attempt 1: The 1000-Image Dataset + V2 Adapter
+I started big. I thought more data = better results, so I gathered 1000 images and used the newest adapter:
+*   **Adapter:** `ostris/zimage_turbo_training_adapter V2`
+*   **Result:** Complete failure. The LoRA didn't capture the anime style at all. The outputs looked generic and lacked any personality from the training data.
+
+### ⚠️ Attempt 2: Curated 100+ Image Dataset + V2 Adapter
+I realized quality beats quantity. I carefully curated a smaller dataset of ~118 high-quality anime images with detailed captions.
+*   **Result:** Better, but still not amazing. The V2 adapter seemed to struggle with strong style transfer. The outputs were "okay," but not the striking anime aesthetic I was aiming for.
+
+### 🔄 Attempt 3: Trying Z-Image-De-Turbo
+I switched gears entirely. I thought maybe training on the non-turbo base model would give me more control:
+*   **Model:** `ostris/Z-Image-De-Turbo`
+*   **Result:** Nothing amazing. While technically capable, it didn't produce the vibrant, stylized anime look I wanted. It felt "flat."
+
+### ✅ Attempt 4: The V1 Adapter — THE WINNER!
+Out of frustration, I went back to the original V1 adapter. And guess what?
+*   **Adapter:** `ostris/zimage_turbo_training_adapter_v1.safetensors`
+*   **Dataset:** My curated 118 anime images
+*   **Result:** **AMAZING!** This was the breakthrough. The V1 adapter, combined with the right settings, finally captured the anime style beautifully. Fast inference, strong style, and consistent quality.
+
+*Sometimes, the "old" version just works better.*
+
+## 💸 The Real Cost: What This Training Cost Me
+Training LoRAs isn't free. Here's the honest breakdown of what I spent on Modal cloud compute to reach this result:
+
+*   **GPU Used:** NVIDIA H200
+*   **Total Training Runs:** 10+
+*   **Total Cost:** ~$60
+*   **Time Invested:** Multiple days of experimentation...
+
+That's $60 and countless hours of debugging, testing different adapters, adjusting hyperparameters, and waiting for training jobs to complete, all to find the perfect combination.
+
+![Training Cost](48ecf48e-20a5-4f5f-8532-a9a8b4d838f0.png)
+
+## ⚙️ The Winning Configuration
+Here is the exact configuration that produced the best results. Feel free to use it as a starting point for your own training!
+
+```yaml
+job: "extension"
+config:
+  name: "aimaginedworlds_turbo"
+  process:
+    - type: "diffusion_trainer"
+      training_folder: "/root/ai-toolkit/modal_output"
+      device: "cuda"
+      trigger_word: "aimaginedworlds"
+      network:
+        type: "lora"
+        linear: 32
+        linear_alpha: 32
+        conv: 16
+        conv_alpha: 16
+      save:
+        dtype: "bf16"
+        save_every: 250
+        max_step_saves_to_keep: 4
+      datasets:
+        - folder_path: "/root/ai-toolkit/training_data/aimaginedworlds"
+          caption_ext: "txt"
+          caption_dropout_rate: 0.05
+          resolution:
+            - 512
+            - 768
+            - 1024
+      train:
+        batch_size: 1
+        steps: 5000
+        gradient_checkpointing: true
+        noise_scheduler: "flowmatch"
+        optimizer: "adamw8bit"
+        lr: 0.0001
+        dtype: "bf16"
+      model:
+        name_or_path: "Tongyi-MAI/Z-Image-Turbo"
+        arch: "zimage:turbo"
+        assistant_lora_path: "ostris/zimage_turbo_training_adapter/zimage_turbo_training_adapter_v1.safetensors"
+      sample:
+        sampler: "flowmatch"
+        sample_every: 250
+        guidance_scale: 1
+        sample_steps: 8
+```
+
+### Key Settings:
+*   **Rank 32/Alpha 32:** The sweet spot for style without overfitting.
+*   **V1 Adapter:** The secret sauce!
+*   **5000 Steps:** Enough for full convergence.
+*   **FlowMatch Scheduler:** Native to Z-Image Turbo.
+
+## 🚀 How to Use This LoRA
+This LoRA was trained specifically for anime/illustration style. It works best when you keep prompts simple and let the trigger word do the heavy lifting.
+
+## 🎨 Showcase
+Here are some examples of what you can create:
+
+| | | |
+|:---:|:---:|:---:|
+| ![Showcase 1](z-image_00268_.png) | ![Showcase 2](z-image_00272_.png) | ![Showcase 3](z-image_00292_.png) |
+| ![Showcase 4](z-image_00301_.png) | ![Showcase 5](z-image_00252_.png) | ![Showcase 6](z-image_00242_.png) |
+
+### ✨ The Trigger Word
+Just add `aimaginedworlds` at the start of your prompt:
+
+> `aimaginedworlds, a girl with blue hair sitting in a cafe`
+
+That's it! You don't need complex prompting, the style is baked in.
+
+### 🔌 Recommended: Z-Image-Turbo Prompt Template Node
+For optimal results with this LoRA, use my **ComfyUI-OllamaGemini** node with the new Z-Image-Turbo prompt template:
+
+🔗 **[ComfyUI-OllamaGemini](https://github.com/AbdallahAlswaiti/ComfyUI-OllamaGemini)**
+
+It does magic prompting using Flux, Veo3.1, Qwen, Gemini, Banana Pro, Imagen4, and more!
+
+![Magic Prompting](swappy-20260101-222728.png)
+
+## ❤️ Support My Work
+Creating high-quality LoRAs takes real time, effort, and money. As you saw above, this project alone cost me ~$60 in cloud compute and days of experimentation.
+
+If this LoRA helps you create beautiful images, please consider supporting my work. Even a small contribution helps me:
+*   🖥️ Cover cloud compute costs for future models
+*   🎨 Train more high-quality anime LoRAs
+*   📚 Share my findings with the community
+
+Every bit of support means the world to me and keeps me going!
+
+## 🛠️ Tools & Credits
+This LoRA was trained using the amazing **AI-Toolkit** by Ostris:
+🔗 [https://github.com/ostris/ai-toolkit](https://github.com/ostris/ai-toolkit)
+
+If you're interested in training your own LoRAs, I highly recommend checking it out. It's powerful, well-documented, and actively maintained!
+
+## 🙏 How You Can Help
+If you found this useful, here are some ways to support:
+*   💸 **Support via PayPal** — Help cover those GPU costs!
+*   📢 **Share your creations** — Tag me so I can see what you make!
+
+[**PayPal**](https://paypal.me/AbdallahAlswaiti)
+
+*Made with ❤️, frustration, and a lot of GPU hours.*

aimaginedworlds_turbo.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d27f3c3ef36791284726d684877f445453b57089bb05d47c4b6aaf4a40b7ae
+size 170128312