benchmarks of a 50% pruned Qwen3.6-35b-a3b and expert-specific quantization technique (made by me) 7.3gb model preforming => 51gb model, exiting to see where I can bring this technique to. I have some more things lined up too. I need a DGX spark😭

H3 🐰💋👠 N$FW LoRA -PinkFluffyBunny lora that truly brings the style and pose -Maximum results achieved at 0.5 str on pruned int8 model. -Use the h3_fl2va_pruned_int8_convrot.safetensors model. Alpha quality so temper expectations 👇😉

i’ve tried cuisines from all over the world, and moroccan cuisine is still the best hands down. if u’ve never tried it, consider this your sign to find a moroccan restaurant asap and order a lamb tajine with prunes. thank me later.

Beyond the BBQ and booze, the American Festival offers delicious bites like fresh gelato, California-grown prunes, olives, cheese, rice and more. Grab your favorite treats and enjoy them while grooving to live American music featuring jazz, pop, and Hawaiian tunes! 🎶🍦 @USDAForeignAg @Freedom250

The SpaceX $SPCX IPO is all the rage. But a little-known Chinese snack food company that makes preserved prunes debuted yesterday and soared 130%, handily beating SPCX —— all because the initials of the company’s name in pinyin are “LLM” 溜溜梅 … Chinese retail investors then went all-in for this “AI” stock. This is how easy it is to make money these days. Back in 2000, you still needed to add “.com” your company name. Now, as long as it sounds like “AI”, that would do.

🖼 Test-time scaling for image editing tends to hand every edit the same compute budget, wasting a lot of it. By allocating budget by difficulty and pruning with edit-specific verification, this work hits up to 2.2x speedup while preserving quality. Title: From Scale to Speed: Adaptive Test-Time Scaling for Image Editing URL: 📝 Overview ADE-CoT is a test-time scaling method tailored to goal-directed image editing. Instead of reusing Image-CoT methods built for text-to-image generation, it combines three strategies, difficulty-aware allocation, edit-specific early verification, and opportunistic stopping, to cut compute substantially while preserving quality. ❓ Challenges Solved Prior methods had three mismatches. ・Fixed sampling budgets waste compute on easy edits that barely improve ・General MLLM scores wrongly prune about 40% of samples that start low but ultimately score high ・Large-scale sampling produces redundant identical correct outputs, adding needless compute 💡 Methodology & Proposed Approach ・It reads edit difficulty, giving easy edits a minimal budget and expanding the search for hard ones ・A one-step preview estimates clean latents from noisy intermediates without extra denoising, making early verification reliable ・Grounded SAM2 checks that only the intended region changed, and DINOv2 embeddings remove redundant candidates ・It generates candidates sequentially and stops, via depth-first opportunistic stopping, once enough intent-aligned results are found 🎯 Use Cases It fits complex pose changes, multi-object removal or replacement, fine-grained regional edits, multi-turn editing, and high-quality editing under compute constraints, and is especially valuable where inference cost matters, like a production image-editing API. 📊 Experimental Results ・On GEdit-Bench, FLUX.1 Kontext is 2.2x, BAGEL 1.8x, and Step1X-Edit 2.0x faster than Best-of-N ・Reasoning efficiency more than doubles on a fixed 32-sample budget, and outcome efficiency rises 4.9x, 2.7x, and 2.9x across three benchmarks ・On hard multi-object edits like "remove the person standing next to the lady in white," it fixes the baseline's misidentification #ImageEditing# #DiffusionModels#