Hugging Face's logo
Steve's picture
7 1 3

Steve

Tiwaz
jeffcookio's profile picture bob-the-42's profile picture John6666's profile picture
·

AI & ML interests

None yet

Recent Activity

new activity about 12 hours ago
black-forest-labs/FLUX.2-klein-9B:Why not Apache 2.0 as the announcment back then said
reacted to DawnC's post with 🚀 2 days ago
VividFlow: Complete AI Image Transformation Platform 🎬🎨✨ Three powerful creative tools in one streamlined workspace. VividFlow combines professional video generation, intelligent background replacement, and artistic style transfer to transform your images with precision and creativity. 🎭 Triple Creative Powers - Cinematic Video Generation transforms static images into smooth motion sequences from 0.5 to 5 seconds. Eight curated motion categories cover portraits, products, landscapes, and artistic content with precision-tuned templates. - Intelligent Background Replacement generates photorealistic scenes from 24 professionally crafted presets spanning studios, natural environments, urban settings, and seasonal atmospheres. Advanced edge refinement handles complex subjects, while the built-in Touch Up tool eliminates artifacts through AI-powered inpainting for flawless results. - Artistic Style Transfer converts photographs into stunning interpretations across six distinct styles including 3D Cartoon, Anime, Watercolor, and Oil Painting. Five balanced style blends create unique hybrid aesthetics, with optional Face Restore preserving subject identity during transformation. ⚡ Optimized Performance Video generation completes in approximately 4 minutes with ongoing optimization targeting sub-60-second processing. Background replacement finishes in 30-40 seconds, while style transfer delivers results in 20-30 seconds. The independent three-tab architecture ensures smooth workflow without performance conflicts. 🎯 Professional Control Seed-based reproducibility guarantees consistent results across all features. Background generation offers flexible composition modes, adjustable edge softening, and instant mask preview. Comprehensive parameter controls enable precise creative direction. 👉 Try it now: https://huggingface.co/spaces/DawnC/VividFlow Support with a ❤️ — your engagement drives priorities! #AI #DeepLearning #ImageToVideo #StyleTransfer #CreativeAI
reacted to MonsterMMORPG's post with ❤️ 3 days ago
Compared Quality and Speed Difference (with CUDA 13 & Sage Attention) of BF16 vs GGUF Q8 vs FP8 Scaled vs NVFP4 for Z Image Turbo, FLUX Dev, FLUX SRPO, FLUX Kontext, FLUX 2 - Full 4K step by step tutorial also published Full 4K tutorial : https://youtu.be/XDzspWgnzxI Check above full 4K tutorial to learn more and see uncompressed original quality and size images It was always wondered how much quality and speed difference exists between BF16, GGUF, FP8 Scaled and NVFP4 precisions. In this tutorial I have compared all these precision and quantization variants for both speed and quality. The results are pretty surprising. Moreover, we have developed and published NVFP4 model quant generator app and FP8 Scaled quant generator apps. The links of the apps are below if you want to use them. Furthermore, upgrading ComfyUI to CUDA 13 with properly compiled libraries is now very much recommended. We have observed some noticeable performance gains with CUDA 13. So for both SwarmUI and ComfyUI solo users, CUDA 13 ComfyUI is now recommended.
View all activity

Organizations

None yet