AI NEWS · Model intelligenceExplore capabilities. Make informed choices. ↗Profiles indexed first · Details continuously enriched
THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Popular searches
85,012 model profiles13202 providers / publishers45 capability categories465 with comparable prices · 30 benchmarked
TText generation▧Image generation▷Video generation⌘Code generation◖Speech synthesis♫Music generation⬡3D modeling▤Document analysis
DISCOVER & COMPARE

Explore AI models 34

Discover models worth your attention

基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

FastH3_GGUFs

realrebelai

基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Input Image→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

**Unpruned, full-weight quantizations of FastVideo's FastH3 Omni 8-Step V1 reference-to-video model, prepared by Rebel AI for ComfyUI experimentation.** > **Full weights, not the pruned release.** These conversions were made from the upstream **14-shard `transformer_ref` BF16 checkpoint**, not the smaller, pruned ComfyUI checkpoint. Quantization reduces numerical precision; it does **not** remove transformer blocks, prune AdaLN parameters, or change the underlying model into a different FastH3 release. FastVideo FastH3 Omni 8-Step V1 is an eight-evaluation distilled derivative of **MiniMax-H3**, designed to generate synchronized video and audio from text and ordered image, video, and audio references. It is a **reference-conditioned (OmniRef / Ref2VA)** model, not the older FastH3 text-to-video / first-and-last-frame-only checkpoint.

Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

FastH3-V2_GGUFs

realrebelai

These GGUFs were converted from the **full official BF16 FastH3 V2 transformer weights** released by FastVideo. FastH3 8-Step V2 is a distilled MiniMax-H3 checkpoint from FastVideo designed to generate synchronized video and audio using only **8 transformer forwards**. For these releases, the complete transformer was reconstructed and converted to the tensor layout expected by ComfyUI before GGUF quantization.

Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

**Community quantizations by Rebel AI** of Black Forest Labs' **FLUX 3 Image Klein** diffusion models, including **Base** and **Step-Distilled** variants. > **Release status: LIVE.** Community GGUF quantizations are available in the Files tab. Download the specific quantization you want to use. Availability varies by file; consult the Files tab for the current releases. Both versions support the FLUX 3 generation/editing workflow family. The settings above are starting points, not GGUF-specific quality guarantees.

Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

Low-VRAM quantizations of **Kandinsky 6.0 Pro 5s** and **Kandinsky 6.0 Pro Distilled 5s** for ComfyUI. Both the standard **50-step Pro model** and the **10-step PiFlow Distilled Pro model** are supported. > **Status: Experimental / Not Fully Tested** > > These are fresh conversions of a newly released architecture. Tested configurations load and run, but broader hardware and workflow testing is still ongoing.

Input Image→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

KREA-2_GGUFs

realrebelai

Quantized GGUF weights for the Krea-2 Base model, optimized for low-VRAM and consumer hardware local workflows via ComfyUI. Krea-2 is a Diffusion Transformer (DiT). Standard GGUF custom nodes will throw an `Unexpected architecture type` error natively. **To run these weights, you must use our patched custom node fork.** Standard loaders do not yet recognize `krea2` architecture tags in GGUF metadata. Clone the following custom node into your `ComfyUI/custom_nodes/` directory: * **Repository:** RealRebelAI/ComfyUI-GGUF_KREA-2

Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

This associates the repository with the main LLaDA-Image-Turbo model as a quantized derivative in the Hugging Face model relationship/quantization tree. The custom ComfyUI runtime loads the quantized transformer while preserving the LLaDA-Image transformer architecture. The LLaDA2-MoE text encoder is provided as Q4_K_M GGUF for substantially lower storage/runtime memory requirements than the original full text encoder.

Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

LTX-2.5_GGUFs

realrebelai

GGUF quantizations of Lightricks' LTX-2.5, converted for ComfyUI with ComfyUI-GGUF. LTX-2.5 generates **video and synchronized audio in a single pass** — a dual-stream DiT with a 4096-wide video path, a 2048-wide audio path, and cross-modal attention joining them. The bf16 transformer is 39 GB. These quants bring it to 8-22 GB. All original licensing terms and usage restrictions carry over from the base model.

Input Text→ Output Video
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

Ming-Image_GGUFs

realrebelai

These are not simple one-pass quants. The diffusion-model files use a **mixed-precision HQ ladder** designed to keep the most sensitive Ming-Image tensors at higher precision while aggressively quantizing the larger bulk weights. 1. Convert the original BF16 diffusion weights into a **shape-preserving BF16 GGUF master**. 2. Quantize that BF16 GGUF directly with `llama-quantize` to create donor files: - `Q8_0` - `Q6_K` - `Q5_K_M` - `Q4_K_M` - `Q3_K_M` - `Q2_K` 3. Build the final `-HQ` models by selecting tensors from those already-quantized donor files. 4. The HQ assembly step copies the existing packed GGUF tensor data directly. It does **not** dequantize and requantize each selected tensor. The `general.architecture` transport metadata used during GGUF conversion is for quantizer/loader compatibility only. It should not be interpreted as Ming-Image being a Lumina2 model.

Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

MiniMax-H3_GGUFs

realrebelai

基础档案已收录,详细介绍后续补充。可先查看厂商、分类与来源。

Category pending
Input Not verified→ Output Not verified
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

MOSS-Image_GGUFs

realrebelai

**SFT-first community quantizations of OpenMOSS's MOSS-Image, prepared by Rebel AI for local text-to-image generation and ComfyUI.** This is a **quantization collection**, not a new model architecture or an official OpenMOSS release. The model, architecture, and original training belong to the **OpenMOSS Team**. The focus here is making MOSS-Image's 5B-parameter diffusion transformer more practical to experiment with on consumer GPUs while preserving a range of quality-versus-size choices. > **Model-tree parent:** This repository is linked to **OpenMOSS-Team/MOSS-Image-SFT** as a **quantization**. **SFT is the primary image-generation variant.** Any Base-labeled checkpoints in the Files tab are independently derived from **OpenMOSS-Team/MOSS-Image-Base** and are included for research, fine-tuning, and comparison; they are not SFT weights.

Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗

High-quality mixed-precision GGUF quantizations of **Qwen-Image 2.1** for use in **ComfyUI** with **ComfyUI-GGUF**. These files were converted from the **Comfy-Org Qwen-Image 2.1 BF16 diffusion model** and preserve the native Comfy tensor naming/layout. No additional tensor-name remapping is required after conversion. > This repository contains the **diffusion model only**. You still need the normal Qwen-Image 2.1 supporting models required by your ComfyUI workflow, including the text encoder and VAE.

Input Text→ Output Image
Price not verifiedCheck multimodal and channel pricing separately
View details ↗
COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ
How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

AI NEWS · From information to decisions

Follow trends. Find tools. Explore models.

Explore AI news ↗Discover AI tools ↗