<h1 id="heading-14">Weekly MidJourney Style Experiment: Last 500 Images</h1>Update (11/02/23) : adding WEEK 3 FFUsion (ALL IN) LoRA of Hot, Rising, and New 🗓 Current Week's Exploration (10.31.23): This week LoRAs are fine-tuned for the🏆'Style Capture &amp; Fusion Showdown' (rejected entry)Week 3 Styles of Hot, Rising, and New MJ categories: 10.31.23 <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1696d989-6594-4778-a9f4-20bfb50bf689/width=525/1696d989-6594-4778-a9f4-20bfb50bf689.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d5c7bc3e-dece-4859-a0bf-8f2f78ed8983/width=525/d5c7bc3e-dece-4859-a0bf-8f2f78ed8983.jpeg" />🔥 Previous Week’s LoRAs (10.23.23): last week styles from the 'Hot', 'Rising', and 'New' category<img src="http://127.0.0.1:7861/file=R:/autoKOR/stable-diffusion-webui/outputs/grids-images/2023-10-23/xyz_grid-0027-2700498413.png" /> <img src="http://127.0.0.1:7861/file=R:/autoKOR/stable-diffusion-webui/outputs/grids-images/2023-10-23/xyz_grid-0023-1421326053.png" /> <img src="http://127.0.0.1:7861/file=R:/autoKOR/stable-diffusion-webui/outputs/grids-images/2023-10-23/xyz_grid-0026-1419367754.png" />A recent experiment conducted using the last 500 images from the 'MidJourney' categories: Hot, Rising, and New. <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/753dc54d-4635-4ef5-be2a-4061ac4e0c95/width=525/753dc54d-4635-4ef5-be2a-4061ac4e0c95.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1187ff44-c9b5-4fa6-af25-8d51b745006a/width=525/1187ff44-c9b5-4fa6-af25-8d51b745006a.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/967ba7b3-d75c-4ef3-9351-dc85f4d112e1/width=525/967ba7b3-d75c-4ef3-9351-dc85f4d112e1.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/65c12d48-f5e0-4582-982d-e91747c784fb/width=525/65c12d48-f5e0-4582-982d-e91747c784fb.jpeg" />Data Acquisition and Integrity:<ul><li>All images were sourced responsibly, with no use of unofficial tools for acquisition.</li><li>The images were obtained using the sanctioned Corporate/Enterprise account.</li></ul>Technical Overview:<ul><li>The images were processed using the <code>ViT-L-14/openai</code> model (quick sloppy run). For testing, the <code>prodigy</code> tool was employed.</li><li>It's important to note that the current quality of results does not align with our typical production standards. However, for those interested in further details, a training set from the official Civitai trainer is available.</li><li>The experiment utilized the capabilities of the Civitai trainer(default out of the box configuration)</li></ul> 09/26/2023 03:48:12 AMSUBMITTED09/26/2023 03:48:40 AMPROCESSING09/26/2023 05:21:46 AMREADY <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1ccb7449-4d6e-4387-ac9c-525921609989/width=525/1ccb7449-4d6e-4387-ac9c-525921609989.jpeg" /><ul><li>Lora FA text encoder, and the Kohya tools, all operating on the H100 80GB.</li></ul>We appreciate your continued interest and support. Further updates will be provided as the experiment progresses.Each one took 20-30min <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/732ba7da-567d-47ae-aa7b-bd6369437230/width=525/732ba7da-567d-47ae-aa7b-bd6369437230.jpeg" /><hr />📂 MidJ_Last_500_-_Experiment.safetensors<ul><li>📅 Date: <code>2023-09-26T02:20:38</code></li><li>🏷️ Title: <code>MidJ_Last_500_-_Experiment</code></li><li>🖼️ Resolution: <code>1024x1024</code></li><li>🧪 Architecture: <code>stable-diffusion-xl-v1-base/lora</code></li><li>🌐 Network Dimensions:<ul><li>Dim/Rank: <code>32.0</code></li><li>Alpha: <code>16.0</code></li></ul></li><li>🔌 Module: <code>networks.lora</code></li><li>🔧 Configurations:<ul><li>Learning Rate: <code>0.0005</code></li><li>UNet LR: <code>0.0005</code></li><li>TE LR: <code>5e-05</code></li><li>Optimizer: <code>bitsandbytes.optim.adamw.AdamW8bit(weight_decay=0.1)</code></li><li>Scheduler: <code>cosine_with_restarts</code></li><li>Warmup Steps: <code>0</code></li><li>Epochs: <code>10</code></li><li>Batches per Epoch: <code>128</code></li><li>Gradient Accumulation Steps: <code>1</code></li><li>Train Images: <code>500</code></li><li>Regularization Images: <code>0</code></li><li>Multires Noise Iterations: <code>6.0</code></li><li>Multires Noise Discount: <code>0.3</code></li><li>Min SNR Gamma: <code>5.0</code></li><li>Zero Terminal SNR: <code>True</code></li><li>Max Gradient Norm: <code>1.0</code></li><li>Clip Skip: <code>1</code></li><li>Dataset Directories: <code>1</code></li><li>Image Count: <code>500 images</code></li></ul></li><li>📈 Stats:<ul><li>UNet Weight (Avg. Magnitude): <code>3.0170</code></li><li>UNet Weight (Avg. Strength): <code>0.0111</code></li><li>Text Encoder (1) - Weight (Avg. Magnitude): <code>1.7304</code></li><li>Text Encoder (1) - Weight (Avg. Strength): <code>0.0087</code></li><li>Text Encoder (2) - Weight (Avg. Magnitude): <code>1.7614</code></li><li>Text Encoder (2) - Weight (Avg. Strength): <code>0.0068</code></li></ul></li></ul>📂 FF-Midj-Last-v0563.safetensors<ul><li>📅 Date: <code>2023-09-26T01:16:09</code></li><li>🏷️ Title: <code>FF-Midj-Last-v0563</code></li><li>🖼️ Resolution: <code>1024x1024</code></li><li>🧪 Architecture: <code>stable-diffusion-xl-v1-base/lora</code></li><li>🌐 Network Dimensions:<ul><li>Dim/Rank: <code>64.0</code></li><li>Alpha: <code>32.0</code></li></ul></li><li>🔌 Module: <code>networks.lora</code></li><li>📈 Stats:<ul><li>UNet Weight (Avg. Magnitude): <code>2.6731</code></li><li>UNet Weight (Avg. Strength): <code>0.0076</code></li><li>Text Encoder (1) - Weight (Avg. Magnitude): <code>2.5809</code></li><li>Text Encoder (1) - Weight (Avg. Strength): <code>0.0091</code></li><li>Text Encoder (2) - Weight (Avg. Magnitude): <code>2.6613</code></li><li>Text Encoder (2) - Weight (Avg. Strength): <code>0.0072</code></li></ul></li></ul><hr />📂 FF-Midj-Rise-v0564.safetensors<ul><li>📅 Date: <code>2023-09-26T02:01:20</code></li><li>🏷️ Title: <code>FF-Midj-Rise-v0564</code></li><li>🖼️ Resolution: <code>1024x1024</code></li><li>🧪 Architecture: <code>stable-diffusion-xl-v1-base/lora</code></li><li>🌐 Network Dimensions:<ul><li>Dim/Rank: <code>64.0</code></li><li>Alpha: <code>32.0</code></li></ul></li><li>🔌 Module: <code>networks.lora</code></li><li>📈 Stats:<ul><li>UNet Weight (Avg. Magnitude): <code>2.6016</code></li><li>UNet Weight (Avg. Strength): <code>0.0074</code></li><li>Text Encoder (1) - Weight (Avg. Magnitude): <code>2.5694</code></li><li>Text Encoder (1) - Weight (Avg. Strength): <code>0.0091</code></li><li>Text Encoder (2) - Weight (Avg. Magnitude): <code>2.6260</code></li><li>Text Encoder (2) - Weight (Avg. Strength): <code>0.0071</code></li></ul></li></ul>📂 FF-Midj-Top-v0564-FA-TX.safetensors<ul><li>📅 Date: <code>2023-09-26T03:21:49</code></li><li>🏷️ Title: <code>FF-Midj-Top-v0564-FA-TX</code></li><li>🖼️ Resolution: <code>1024x1024</code></li><li>🧪 Architecture: <code>stable-diffusion-xl-v1-base/lora</code></li><li>🌐 Network Dimensions:<ul><li>Dim/Rank: <code>64.0</code></li><li>Alpha: <code>64.0</code></li></ul></li><li>🔌 Module: <code>networks.lora_fa</code></li><li>📈 Stats:<ul><li>Text Encoder (1) - Weight (Avg. Magnitude): <code>5.8341</code></li><li>Text Encoder (1) - Weight (Avg. Strength): <code>0.0191</code></li><li>Text Encoder (2) - Weight (Avg. Magnitude): <code>6.0269</code></li><li>Text Encoder (2) - Weight (Avg. Strength): <code>0.0153</code></li></ul></li><li>⚠️ Note: No UNet found in this LoRA.</li></ul><h3 id="heading-47">🌐 <a target="_blank" rel="ugc" href="http://FFusion.ai">FFusion.ai</a> Contact Information</h3>Proudly maintained by Source Code Bulgaria Ltd &amp; Black Swan Technologies.<ul><li>📧 Email Us: <a target="_blank" rel="ugc" href="mailto:di@ffusion.ai">di@ffusion.ai</a> - For inquiries or support.</li><li>🌍 Locations: Sofia | Istanbul | London</li></ul>Connect with Us:<ul><li>🐙 <a target="_blank" rel="ugc" href="https://github.com/1e-2">GitHub</a></li><li>😊 <a target="_blank" rel="ugc" href="https://huggingface.co/FFusion">Hugging </a><a target="_new" rel="ugc" href="https://chat.openai.com/c/4440256e-8c09-4f2e-ab25-1c9abfbf67f9#">Face</a></li><li>💡 <a target="_blank" rel="ugc" href="https://civarchive.com/user/idle/models">Civitai</a></li></ul>Our Websites:<ul><li>🌐 <a target="_blank" rel="ugc" href="http://FFusion.ai">FFusion.ai</a></li><li>🌌 <a target="_blank" rel="ugc" href="http://FFAI.eu">FFAI.eu</a></li><li>🔗 <a target="_blank" rel="ugc" href="http://1e-2.com">1e-2.com</a></li></ul>

FF Style: HOT, RISING NEW - MidJourney Experiment

📂 MidJ_Last_500_-_Experiment.safetensors<ul><li>📅 Date: <code>2023-09-26T02:20:38</code></li><li>🏷️ Title: <code>MidJ_Last_500_-_Experiment</code></li><li>🖼️ Resolution: <code>1024x1024</code></li><li>🧪 Architecture: <code>stable-diffusion-xl-v1-base/lora</code></li><li>🌐 Network Dimensions:<ul><li>Dim/Rank: <code>32.0</code></li><li>Alpha: <code>16.0</code></li></ul></li><li>🔌 Module: <code>networks.lora</code></li><li>🔧 Configurations:<ul><li>Learning Rate: <code>0.0005</code></li><li>UNet LR: <code>0.0005</code></li><li>TE LR: <code>5e-05</code></li><li>Optimizer: <code>bitsandbytes.optim.adamw.AdamW8bit(weight_decay=0.1)</code></li><li>Scheduler: <code>cosine_with_restarts</code></li><li>Warmup Steps: <code>0</code></li><li>Epochs: <code>10</code></li><li>Batches per Epoch: <code>128</code></li><li>Gradient Accumulation Steps: <code>1</code></li><li>Train Images: <code>500</code></li><li>Regularization Images: <code>0</code></li><li>Multires Noise Iterations: <code>6.0</code></li><li>Multires Noise Discount: <code>0.3</code></li><li>Min SNR Gamma: <code>5.0</code></li><li>Zero Terminal SNR: <code>True</code></li><li>Max Gradient Norm: <code>1.0</code></li><li>Clip Skip: <code>1</code></li><li>Dataset Directories: <code>1</code></li><li>Image Count: <code>500 images</code></li></ul></li><li>📈 Stats:<ul><li>UNet Weight (Avg. Magnitude): <code>3.0170</code></li><li>UNet Weight (Avg. Strength): <code>0.0111</code></li><li>Text Encoder (1) - Weight (Avg. Magnitude): <code>1.7304</code></li><li>Text Encoder (1) - Weight (Avg. Strength): <code>0.0087</code></li><li>Text Encoder (2) - Weight (Avg. Magnitude): <code>1.7614</code></li><li>Text Encoder (2) - Weight (Avg. Strength): <code>0.0068</code></li></ul></li></ul>

Files with SHA256: 30aed535255a09f967d0c4dd8f3abe84d45714da2c10a6a28f6b819de9db45e6