Generates synchronized, streaming spatial audio from panoramic video and text prompts using a causal autoregressive diffusion transformer. Combines Spatial Video-Audio Contrastive (SVAC) alignment and online direct preference optimization (ODPO) to improve spatial perception, plus an automated annotation pipeline and public demos.
Contains a sanitized Claude Code (Fable 5) JSONL transcript of a session that procedurally built a Boeing 747 in Three.js, including assistant messages, tool calls, and base64 screenshots — useful for studying agent trace, tool use, and vision self‑verification workflows.
Provides ComfyUI-ready repackaged checkpoints of the Krea 2 image model family for local text-to-image workflows. Includes RAW (undistilled base for fine-tuning and LoRA training) and Turbo (8-step distilled checkpoint for fast inference), using a Qwen Image VAE and Qwen3‑VL encoder.
Converts low‑poly 3D viewport or game/CG renders into photorealistic cinematic video while preserving the input's composition, camera motion and layout; offers Light and Strong LoRA variants to trade fidelity for aggressive photorealism.
Applies or repositions directional sunlight in outdoor images by using a LoRA trained for Flux2Klein 9B to match a reference sun elevation and rotation. Workflow uses an overcast intermediate and a sphere (ball) reference; includes a ComfyUI node and Blender scene for rendering the reference.
Generates real-time, infinite-length interactive videos of voice-controllable digital characters — 540p at up to 42 FPS on consumer GPUs. Uses TurboDiffusion and TurboServe to maintain temporal coherence without blur or drift, and accepts custom person, anime, or pet images plus selectable voice tones.
Instruction-driven LoRA fine‑tune for identity‑preserving image edits: give an image plus a plain‑language instruction and it edits pose, outfit, objects or scene while keeping unasked content and subject likeness. Requires the ComfyUI‑Krea2Edit node pack; distributed under the Krea 2 Community License.
Generates image-to-video world-model outputs using a distilled 14B causal model optimized for chunked, KV-cached inference across long-horizon interactive scenes; offers a real-time 'causal-fast' variant capable of driving near‑real‑time video streams and an agentic harness for action-driven scene synthesis (CC BY‑NC‑SA).
Provides repackaged Mage-Flow model files formatted for ComfyUI, including multiple diffusion variants (bf16, int8, turbo, edit), a Qwen text encoder and a VAE — organized in a ComfyUI directory layout for drop-in use.
A small public sample of egocentric human demonstration video with synchronized 3D hand and body pose annotations for imitation learning and embodied-AI research. Delivered in Parquet and common multimodal packages (LeRobot, MCAP) for schema inspection before requesting gated access to larger EgoSuite releases.
Conditions a MiniMax‑H3 video generator with a single ControlNet‑Union checkpoint to accept Canny, Depth, HED, MLSD or Pose control videos and run video inpainting. Guidance‑distilled for one‑pass inference; requires the base MiniMax‑H3 weights and specific control-branch config.
Provides an unattended text-to-video-and-audio streaming toolkit built around FastH3 (a 4-step distillation of MiniMax-H3): generation/retime/HTTP push scripts, a 221-scene prompt library, checkpoint conversion and ComfyUI workflows to run a continuous local stream.