Tools, frameworks, and models for local AI
8 resources found for "Diffusion"
The most advanced open image model: excellent prompt adherence, solid anatomy, full fine-tuning. The standard for serious work.
Very few steps, high quality, and strong text rendering. The distilled FLUX variant, built for speed.
326M-parameter autoregressive diffusion model for interactive real-time humanoid motion: online text prompts, kinematic constraints (root trajectories, keyframes, sparse poses) and sequences up to 8 seconds. Trained on Bones Rigplay 1 (27-joint Core skeleton, 20 fps), optimized for NVIDIA Ampere, Hopper and Blackwell GPUs. NVIDIA Open Model Agreement license, commercial use allowed. On Hugging Face since October 7, 2026.
Post-trained 4B robot-policy checkpoint on the Cosmos3-Edge base: from natural-language instructions and visual observations of the DROID robot it generates action trajectories for manipulation tasks. Mixture-of-Transformers architecture (autoregressive tower + diffusion transformer), OpenMDW 1.1 license, commercial and non-commercial use.
Alibaba's 20B (MMDiT) image-generation model: excellent in-image text comprehension, precise editing, and an Apache 2.0 license. The base of the Qwen-Image family, of which 2.1 is the compact 7B variant.
The image-generation classic: fast, light, and with the largest LoRA/ControlNet ecosystem of all. Perfect for 6-8GB GPUs.
The current standard for photoreal and artistic images at 1024px. Better prompt adherence and more coherent composition than SD 1.5.
Turns an image into a short ~2s video clip. The entry point for local video generation; 16GB VRAM recommended.
