Tag

RuneXX/LTX-2.3-Workflows

ComfyUI workflows that run LTX‑2.3 split models to produce text→video, image→video and audio→video pipelines. Uses extracted/split safetensor or GGUF files so models load more modularly; requires up‑to‑date ComfyUI, KJNodes and ComfyUI‑GGUF.

Dramabox

Generates expressive, prompt-driven text-to-speech audio with optional 10-second voice cloning; prompts control speaker identity, emotion, pauses and nonverbal sounds. An IC‑LoRA fine-tune of LTX‑2.3 that applies an imperceptible Resemble Perth watermark.

Gemma 4 E4B-it Assistant

Provides a lightweight assistant (draft) model for Gemma 4 E4B used in speculative-decoding pipelines — it predicts token drafts that the target model verifies in parallel, enabling up to ~2× decoding speedups while preserving identical final outputs. Useful for low-latency, multimodal assistant and on-device scenarios.

gemma-4-31B-it-DFlash

Draft model for speculative decoding that uses a lightweight block-diffusion drafter to propose multiple tokens in parallel; designed to pair with google/gemma-4-31B-it and accelerate autoregressive text generation (official benchmarks report up to ~5.8× throughput).

HiDream-O1-Image

Generates and edits high-resolution images (up to 2048×2048) from text and reference images, plus subject-driven personalization. Implements a pixel-level unified transformer that encodes raw pixels and text in one token space and includes a reasoning-driven prompt agent for layout and text rendering.

SANA-WM (Bidirectional)

Generates minute-scale, 720p videos from a single image using a 2.6B image-to-video diffusion transformer with precise 6‑DoF camera control and an optional LTX‑2 refiner; designed for long-context, memory-efficient modeling but requires large refiner checkpoints (~41 GB).

google/gemma-4-12B-it

Instruction-tuned, unified Gemma 4 12B multimodal model that accepts text, image and audio inputs and generates text outputs locally. Encoder-free design reduces multimodal latency and fits on consumer devices while offering long-context support and native thinking/system-prompt features.

Gemma 4 12B Unified

A 12B unified, encoder-free multimodal model that directly ingests text, images and audio and returns text; supports very long contexts (up to 256K tokens), native function-calling/thinking modes, and small-model deployment for local or on-device use.

unsloth/gemma-4-12b-it-GGUF

A GGUF-quantized, locally runnable build of Gemma 4 12B Unified (image-text-to-text) packaged by unsloth; preserves multimodal (image/audio) input support under an Apache-2.0 license and is compatible with common GGUF runtimes and Unsloth Studio.

google/gemma-4-12B-it-qat-q4_0-gguf

Provides a GGUF-ready QAT (Q4_0) quantized build of Gemma 4 12B that preserves near-bfloat16 quality while reducing memory footprint for local inference; compatible with Transformers-based and GGUF runtimes.

Gemma-4-12B-OBLITERATED

A surgically modified Gemma 4 (12B) that removes refusal behavior while preserving benchmark parity; released as an uncensored research artifact with GGUF quantizations for local inference and red‑team/alignment evaluation.

unsloth/gemma-4-12B-it-qat-GGUF

GGUF-format QAT (quantization-aware training) build of Gemma 4 12B that reduces memory needs for local or lightweight inference while preserving near bfloat16 quality. Ready for any-to-any conversational pipelines and ecosystem deployment.