Update README.md

README.md

@@ -3,33 +3,39 @@ 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
 ---
-<h1>RealFlux 1.0b Model Training (Third Attempt)</h1>
+<b>It's important! Read it!</b><br>
+The model is still in the training phase. This is not the final version. This version of the model may contain errors in anatomy and text, and it may also contain artifacts. I tried to fix them, and this is the best result so far compared to what was achieved previously.<br>
 
-<h2>Stage 1: Data Preparation</h2>
-    <ul>
-        <li>[ ☑ ] Collect images for the dataset</li>
-        <li>[ ☑ ] Image captioning</li>
-    </ul>
+<b>You can support me directly on Boosty - https://boosty.to/sg_161222</b>
 
-<h2>Stage 2: Model Training</h2>
-    <ul>
-        <li>[ ☑ ] Prepare dataset for model input</li>
-        <li>[ ☑ ] Model training</li>
-    </ul>
+<h2>Using the Model</h2>
+<b>Compact Version</b> The Compact version already includes VAE, Clip-L, and T5XXL.
+  <ul>
+      <li>For ComfyUI, place the model in the following path: ComfyUI_windows_portable\ComfyUI\models\checkpoints</li>
+      <li>For Forge, place the model in the following path: webui_forge_cu121_torch231\webui\models\Stable-diffusion</li>
+  </ul>
 
-<h2>Stage 3: Testing</h2>
-    <ul>
-        <li>[ ☑ ] Dev Model testing</li>
-    </ul>
+<b>Transformer Version (Unet)</b> The Transformer version requires you to have Flux VAE, Clip-L, and T5XXL.
+  <ul>
+      <li>For ComfyUI:</li>
+          <ul>
+              <li>Place the VAE in the following path: ComfyUI_windows_portable\ComfyUI\models\vae</li>
+              <li>Place Clip-L and T5XXL in the following path: ComfyUI_windows_portable\ComfyUI\models\clip</li>
+              <li>Place the Transformer (Unet) in the following path: ComfyUI_windows_portable\ComfyUI\models\unet</li>
+          </ul>
+  </ul>
 
-<h2>Stage 4: Release</h2>
-    <ul>
-        <li>[ ▶ / ▶ ] Release Dev Compact Version and Transformer</li>
-        <li>[ ☐ ] Release GGUF Q8 version</li>
-    </ul>
+Then you can use the Basic Workflow by moving the image into the ComfyUI workspace.
+
+<h2>Optimal Generation Settings</h2>
 
-<h2>Comments</h2>
+<b>Sampling Method and Schedule Type:</b> Euler Beta<br>
+<b>Sampling Steps:</b> 20+<br>
+<b>Distilled CFG Scale:</b> 3.5<br>
+<b>CFG Scale:</b> 1.0
 
-<p>The first version of the model turned out to be unsuccessful due to significant anatomical errors. The second version of the model is being trained on a reassembled dataset with better-chosen training parameters.</p>
-  
-<p>The second version of the model has even fewer anatomical errors and text errors. The model has been sent for refinement with a slightly modified dataset.</p>
+<h2>Limitations of RealFlux 1.0b Dev</h2>
+    <ul>
+        <li>There may be issues with anatomy.</li>
+        <li>There may be issues with generating images in the anime style (the quality of generations will be improved in future versions).</li>
+    </ul>