So a cool thing happened,
Nomic/GPT4ALL released a "Reasoning/Thinking"(QwQ/o1/o3 type) Model using JavaScript functions to calculate things like the haversine function for distance between two places and so on, it's VERY cool the complex calculative/recursive AI in such a small package..

I was able to adapt their methods to one of my small models "Replicant" 2gb and created a new model with importance matrix Quantization using "THE_KEY" Dataset for better inference in the coding model I pulled from Whiterabbitneo's Qwen2.5 model... I give you Reasoning Rabbit.. enjoy

https://huggingface.co/IntelligentEstate/o3-ReasoningRabbit_Q2.5-Cd-7B-IQ4_XS-GGUF
-IntelligentEstate/o3-ReasoningRabbit_Q2.5-Cd-7B-IQ4_XS-GGUF

https://huggingface.co/IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF
IntelligentEstate/Replicant_Warder-o3-Q2.5_3B-iQ5_K_S-GGUF

-WhiteRabbitNeo/WhiteRabbitNeo-2.5-Qwen-2.5-Coder-7B

liked a Space about 1 year ago

Moonshine Web

🌙

137

Real-time in-browser speech recognition

reacted to MonsterMMORPG's post with 🔥 about 1 year ago

Post

2814

Simple prompt 2x latent upscaled FLUX - Fine Tuning / DreamBooth Images - Can be trained on as low as 6 GB GPUs - Each image 2048x2048 pixels

AI Photos of Yourself - Workflow Guide
Step 1: Initial Setup
Follow any standard FLUX Fine-Tuning / DreamBooth tutorial of your choice

You can also follow mine step by step : https://youtu.be/FvpWy1x5etM

Step 2: Data Collection
Gather high-quality photos of yourself

I used a Poco X6 Pro (mid-tier phone) with good results

Ensure good variety in poses and lighting

Step 3: Training
Use "ohwx man" as the only caption for all images

Keep it simple - no complex descriptions needed

Step 4: Testing & Optimization
Use SwarmUI grid to find the optimal checkpoint

Test different variations to find what works best

Step 5: Generation Settings
Upscale Parameters:

Scale: 2x

Refiner Control: 0.6

Model: RealESRGAN_x4plus.pth

Prompt Used:

photograph of ohwx man wearing an amazing ultra expensive suit on a luxury studio<segment:yolo-face_yolov9c.pt-1,0.7,0.5>photograph of ohwx man
Note: The model naturally generated smiling expressions since the training dataset included many smiling photos.

Note: yolo-face_yolov9c.pt used to mask face and auto inpaint face to improve distant shot face quality