AI Models

BAAI (Beijing Academy of AI) open-weight English embedding model with 335M parameters. Returns 1024-dim vectors and was a top MTEB English retrieval model on release. The v1.5 update improved similarity distribution so it works well without a query instruction prefix for symmetric tasks. A widely used open alternative to hosted embeddings.

BAAI multilingual embedding model covering 100+ languages with an 8192-token context. M3 stands for its multi-functionality (dense, sparse and ColBERT-style multi-vector retrieval), multilinguality and multi-granularity over long documents. Returns 1024-dim dense vectors and is a strong open choice for cross-lingual and long-text retrieval.

The original Bio_ClinicalBERT from Alsentzer et al., a BERT model initialized from BioBERT and further pretrained on all MIMIC-III clinical notes. Served as a fill-mask endpoint it predicts masked tokens in clinical text and produces clinical embeddings. It is the standard encoder backbone behind many downstream clinical NLP fine-tunes.

Token-classification model from d4data that tags 84 biomedical entity types in clinical and medical text, including disease, sign, symptom, medication, dosage, lab value, body part and procedure. Trained on the Maccrobat clinical case corpus on a DistilBERT base, so it runs cheaply for high-volume tagging.

Salesforce BLIP. Vision-language model for image captioning and visual question answering. Given an image it writes a short natural-language caption, or answers a question about the image when one is supplied. A widely used baseline for automatic captioning.

Anthropic Claude 3.5 Sonnet with image input. 200k context, strong on dense documents, tables, charts and handwriting. Reliable structured extraction from screenshots and scans.

Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.

Anthropic's April 2026 flagship. 87.6% on SWE-bench Verified, 3x higher image resolution, output self-verification, vision + reasoning.

Anthropic's most capable Opus-tier model. State of the art on long-horizon agentic work, coding and knowledge tasks, with a 1M-token context window at standard pricing.

Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.

Anthropic's balanced mid-tier model from February 2026. Best price/performance for production workloads: 5x cheaper than Opus, near-flagship quality.

pharmapsychotic's CLIP Interrogator. Takes an image and produces a Stable-Diffusion-style text prompt by combining BLIP captioning with CLIP to rank likely subjects, artists, mediums and styles. Commonly used to reverse-engineer a prompt from an existing picture.

Mistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.

DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.

DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.

Monocular depth-estimation model trained on 595k labeled and 62M unlabeled images. Strong zero-shot generalization in indoor and outdoor scenes.

ElevenLabs' most natural-sounding TTS model. Supports 29 languages with emotional range.

Meta AI 650M-parameter protein language model trained on UniRef50 sequences. Feed it an amino-acid sequence and the per-residue hidden states act as learned protein embeddings, used for structure prediction, variant-effect and function tasks. This 33-layer checkpoint is the common balance of quality and cost in the ESM-2 family.

Black Forest Labs' flagship text-to-image model. Faster generation than FLUX.1 Pro at higher prompt adherence, with strong photorealism and reliable spatial composition. Runs as a hosted Replicate model.

FLUX 1.1 Pro in ultra mode. Up to 4 megapixel images with raw mode for photorealism.

FLUX 1.1 Pro in Ultra mode by Black Forest Labs. Generates up to 4 megapixel images with a raw mode for less processed, more natural-looking photography. Best FLUX option when output resolution and fine detail matter.

Black Forest Labs' development model. Fast, high-quality image generation with LoRA support.

Google Gemini 1.5 Pro with native multimodal input. Reads images, long PDFs, audio and video in up to a 2M-token context, useful for whole-document and long-video understanding.

Google's fastest multimodal model. Supports text, images, audio, and video input.

Google's latest thinking model. Excels at reasoning, coding, math, and science with massive context window.

Google's April 2026 fast multimodal model. Combines Gemini 3 Pro's reasoning with Flash-tier latency and price. Default model in the Gemini app.

Google DeepMind's February 2026 flagship. 2M-token context, native multimodal (text/image/audio/video), Deep Think reasoning.

Google DeepMind's Imagen 4 text-to-image model, hosted on Replicate. Sharp detail, accurate text rendering, and strong prompt adherence across photographic and illustrated styles. Outputs up to 2K resolution.

Google's Imagen 4. Text-to-image with strong photorealism and improved typography support.

Premium Imagen 4 tier. Highest fidelity, prompt adherence and typography quality from Google.

Google's state-of-the-art video generation model. Simulates real-world physics with various visual styles.

Google's Veo 3. High-fidelity text-to-video with native audio generation, up to 8s clips.

Google's Veo 3 served via Replicate. Text-to-video with native synchronized audio generation. High-fidelity motion and scene coherence in short clips.

Latest Veo with image-to-video and context-aware audio

OpenAI's newest flagship model. Improved reasoning, instruction following, and coding over GPT-4o.

OpenAI's most capable multimodal model. Excellent for complex reasoning, coding, and creative tasks.

OpenAI's GPT-4o with native image input. Handles text and images in a single context, 128k window, strong on chart reading, document QA, screenshots and visual reasoning.

OpenAI's unified flagship combining GPT and o-series reasoning into one model. 1M context, multimodal, top SWE-Bench Pro and OSWorld scores.

OpenAI's efficient mid-tier model. 2x faster than its predecessor, 400k context, approaches GPT-5.4 quality on SWE-Bench Pro at a fraction of the cost.

OpenAI's current flagship chat model (released April 2026). Strongest general reasoning, coding and tool use in the GPT-5 line, with vision input and a large context window.

xAI's flagship reasoning model with vision and tool use. 256k context, strong at complex reasoning and STEM tasks.

xAI's Grok 4.20 reasoning snapshot. Runs an extended thinking pass before answering for multi-step analysis, math and STEM, with a 1M token context window and strong agentic tool calling.

xAI's May 2026 flagship. 1M context, vision, always-on reasoning, real-time X/web retrieval via DeepSearch.

Tencent's HunyuanVideo, a 13B open-weights text-to-video diffusion transformer. Produces high-motion, photorealistic clips with smooth temporal consistency and was one of the first open models to rival closed systems on motion quality.

SDXL fine-tune by galleri5 for slick flat icons and pop constructivist graphics with thick edges. Trained on Bing generations, it produces clean single-subject icon art that suits app icons, badges and UI glyphs. Raster output, not true vector.

Ideogram's flagship text-to-image model with industry-leading text rendering and prompt adherence.

The highest-quality tier of Ideogram v3. Improved photorealism and prompt adherence over v2 while keeping Ideogram's best-in-class text rendering. Supports style references and inline text layout.

Whisper Large v3 wrapped with Hugging Face Transformers optimizations (batched inference, flash attention) for very high throughput. Transcribes hours of audio in minutes on a single GPU. Maintained by Vaibhav Srivastav. Good when you need bulk transcription fast.

InstantID makes realistic portraits of a real person from a single reference photo without per-user training. Combines a face encoder with an IdentityNet adapter on SDXL to keep identity and pose while following a text prompt, so it is fast and tuning-free.

ResNet50 from the TIA Toolbox model zoo, trained on the Kather100K dataset of 100,000 hematoxylin-and-eosin colorectal histology patches. It classifies a tissue tile into one of nine categories such as tumor epithelium, stroma, lymphocytes, mucus, smooth muscle, debris, adipose, background and normal mucosa. Research use only, not a diagnostic device.

Moonshot AI's 1T-parameter MoE model. Industry-leading agentic coding and tool-use benchmarks.

Kuaishou's Kling v2.1, generating 5 and 10 second videos at 720p or 1080p from text or an image. Known for cinematic camera work and realistic physical motion, available on Replicate via the official KwaiVGI account.

Kuaishou's premium Kling v2.1 Master. Generates 1080p 5s and 10s clips from text or an image with strong dynamics and prompt adherence. The top tier of the Kling 2.1 family.

Cinematic video up to 15s with multi-shot and native audio

Most versatile: multi-reference images, video editing, native audio

Token-classification model that extracts 41 medical entity types from clinical text, such as disease, medication, dosage, frequency, lab test, sign and symptom. Fine-tuned on a DeBERTa v3 base, which gives more accurate spans than older BERT-based taggers on the same corpus.

The latest Midjourney model. Industry-leading aesthetic quality and prompt adherence for image generation.

MiniMax Hailuo 02 on Replicate. Text-to-video and image-to-video producing 6s or 10s clips at 768p standard or 1080p pro. Known for accurate real-world physics and stable motion.

MiniMax's 456B hybrid lightning-attention model with native 4M-token context. Industry-leading long-context.

Meta's music generation model. Generate up to 1 minute of music from text descriptions.

Nomic AI open embedding model with a fully reproducible training pipeline (open weights, data and code). Supports an 8192-token context and Matryoshka representation learning, so you can truncate the 768-dim output down to 64 dims with graceful quality loss. Uses task prefixes like search_query and search_document.

OpenAI's reasoning model optimized for STEM tasks, coding, and math. Uses chain-of-thought reasoning.

OpenAI's second-generation Sora video model. Realistic motion, improved physics, audio support.

OpenAI's highest-quality embedding model. Returns 3072-dim vectors by default and supports reducing dimensions via the dimensions parameter. Outperforms text-embedding-3-small and the older ada-002 on MTEB and multilingual MIRACL retrieval benchmarks, for cases where accuracy matters more than cost.

OpenAI's small, low-cost embedding model. Returns 1536-dim vectors by default and supports shortening output dimensions via the dimensions parameter without retraining. Replaced text-embedding-ada-002 with better retrieval quality at a fraction of the price, and is the default choice for general-purpose semantic search and RAG.

Perplexity's premium web-grounded search model with multi-step reasoning over live sources.

Turns any single selfie into a clean professional headshot using FLUX Kontext image editing. Keeps the person's face while swapping to business attire, a studio background and even lighting. Aimed at LinkedIn-style profile photos.

Sentence-transformers model fine-tuned from Microsoft PubMedBERT on PubMed title-abstract pairs by the NeuML team. Produces 768-dim sentence embeddings tuned for biomedical semantic search and similarity, and is the embedding backbone behind the paperai and txtai medical search tools.

Recraft's faster, cheaper vector model. Outputs editable SVG paths instead of raster pixels, so logos, icons and flat illustrations scale to any size without blur. Defaults to a vector_illustration style and supports line art and engraving looks. Hosted API only.

Recraft's text-to-image model that topped the Hugging Face text-to-image arena at release. Strong long-text rendering, brand-style consistency, and precise control over image dimensions and color palettes.

Recraft's raster-to-vector converter. Takes a PNG or JPG and traces it into a clean SVG with precise vector paths, aimed at logos, icons and graphics that need to scale. Image-to-SVG counterpart to Recraft's text-to-SVG models.

Top-ranked for motion quality and visual fidelity

Runway's Gen-4 Turbo on Replicate. Fast image-to-video generation producing 5s and 10s clips at 720p with strong character and scene consistency across shots.

Meta Segment Anything 2. Promptable segmentation across images and video with temporal memory. Zero-shot, point/box/mask prompts, fast on a single H100.

OpenAI video generation model. Create realistic and imaginative videos from text prompts up to 20 seconds.

AllenAI document-level embedding model for scientific papers. Built on SciBERT and trained on the citation graph so that papers citing each other land close together. Feed it a title plus abstract and it returns one 768-dim vector per paper, useful for recommendation, clustering and citation-based retrieval.

Stability AI's SDXL 1.0 with the optional refiner. The 3.5B base plus 6.6B ensemble UNet that became the default open image model before FLUX. Good for fine-tuning and LoRAs, broad community support.

fofr's sticker generator that outputs graphics with transparent backgrounds, so the result drops straight into chat apps or print sheets. Runs an SDXL-based pipeline at high speed (default 17 steps) and returns die-cut style art without manual background removal.

Vision Transformer (ViT) fine-tuned on chest x-ray images for multi-class thoracic findings. Given a single frontal chest radiograph it returns class probabilities across several disease categories. One of the more downloaded chest x-ray classifiers on the Hugging Face Hub. Research and education only, not a diagnostic tool.

Voyage's general-purpose embedding model. 1024 dims, 32k context, strong retrieval performance.

OpenAI's Whisper running on Replicate. General-purpose speech recognition trained on 680k hours of multilingual audio. Transcribes and translates 99 languages, robust to accents and background noise, and outputs plain text, segments, or word-level timestamps.

OpenAI's Whisper model. State-of-the-art speech recognition supporting 99+ languages.

OpenAI's distilled Whisper Large v3. ~216x realtime, 99+ languages, MIT-licensed weights.

Background removal model from 851-Labs that outputs a clean cutout with a transparent alpha channel. One of the most-run background removers on Replicate, handles people, products and objects on busy backgrounds.

Product advertising photo generator. You upload a cut-out product shot and a prompt describing the scene; it places the product on a new generated background with matching lighting and shadows, so a plain packshot becomes an ecommerce or ad-ready hero image without a photo studio.

AI21's flagship hybrid Mamba-Transformer model with a 256k context window for long-document tasks.

Cost-efficient hybrid Mamba-Transformer model with 256k context. Tuned for high-throughput RAG.

Plug-and-play motion module that animates personalized Stable Diffusion models without further training. 16-frame clips at 512x512.

ByteDance distillation of AnimateDiff. 4-step sampling for over 10x faster inference at comparable quality to multi-step base model.

Latent-diffusion model for general-purpose text-to-audio. Generates speech, music, and sound effects with a unified prior.

fal.ai's fully open-source 6.8B flow-based text-to-image model. Up to 1536x1536 resolution.

Suno's text-to-audio model. Generates realistic speech, music, and sound effects.

BioBERT fine-tuned on the NCBI Disease corpus for disease-name recognition. Given biomedical text it tags spans that mention a disease or condition, using BIO labels. Useful for pulling diagnoses and disease mentions out of abstracts, case reports and clinical notes.

DMIS-Lab (Korea University) BERT-base initialized from English BERT and further pretrained on PubMed abstracts. Used as a feature extractor it yields 768-dim contextual embeddings tuned for biomedical text mining tasks such as NER, relation extraction and biomedical question answering.

Microsoft BiomedBERT (formerly PubMedBERT) pretrained from scratch on PubMed abstracts with a domain-specific vocabulary, rather than adapting a general model. As a feature extractor it gives 768-dim biomedical embeddings and set the original state of the art on the BLURB biomedical NLP benchmark.

BiRefNet high-resolution dichotomous image segmentation for background removal. Bilateral reference network that produces sharp matting on fine detail like hair, fur and thin structures, often cleaner than older U2Net or rembg models.

Salesforce BLIP large checkpoint for image captioning, served through Hugging Face Inference. Given a photo it returns a short English caption. The large variant gives more accurate captions than the base model and is a common drop-in for alt-text and image indexing.

Image classifier by prithivMLmods that labels a bone x-ray as Fractured or Not Fractured. Given a single radiograph it returns binary class scores. One of the more downloaded fracture classifiers on the Hub. Research and education only, not a diagnostic tool.

BRIA AI's commercial background removal model trained on fully licensed data. Produces accurate cutouts for e-commerce and design, with attention to clean edges around products and people.

BRIA's first commercial-safe background-removal model. Trained on fully-licensed data, suitable for production e-commerce and design pipelines.

BRIA's professional background-removal model trained on fully-licensed data. Commercial-safe.

Microsoft Research pipeline by Ziyu Wan et al. that restores scanned old photos, removing scratches, dust and fading and optionally enhancing faces in one pass.

ByteDance's Seedance 1 Pro on Replicate. Text-to-video and image-to-video producing 5s or 10s clips at 480p or 1080p. Strong motion quality and prompt following from the Seedance family.

Cartesia's ultra-low-latency TTS (~90ms TTFB). State-space model with voice cloning support.

catacolabs Cartoonify turns a photo into a flat cartoon illustration. Takes a single image and returns a stylized cartoon version with clean shapes and bold outlines. Straightforward one-input model for avatars and profile pictures.

Content-Consistent Super-Resolution model. Reduces hallucination compared to typical diffusion-based upscalers while keeping perceptual quality high.

Champ controllable human image animation. Uses 3D parametric guidance (SMPL) for realistic full-body motion transfer from a single reference image.

Resemble AI's open Chatterbox TTS. Zero-shot voice cloning from a short audio prompt with an exaggeration control for emotion intensity, plus CFG weight to balance pacing and fidelity.

High-resolution image upscaler with creative detail re-imagination via SD-based hallucination. Strong for photography and product shots.

Anthropic's fast and affordable model. Great for quick tasks, summarization, and simple coding.

Anthropic's fastest and cheapest 4.x model. Strong vision and tool use at ultra-low latency, ideal for high-concurrency workloads.

Text-classification model from Betty van Aken that decides whether a medical condition mentioned in a clinical note is present, absent or possible. The target entity is marked in the input with [entity] tags, and the model returns the assertion status. Built on Bio_ClinicalBERT and trained on the 2010 i2b2/VA assertion data.

Token-classification model that tags the three core i2b2 clinical entity types in patient notes: problem, test and treatment. Given a sentence from a discharge summary or progress note it marks which spans are medical problems, which are diagnostic tests and which are treatments or medications.

Meta's 13B Code Llama tuned for instruction following. A faster mid-size option for code generation and completion, supporting infilling for inserting code at a cursor position. Served on Replicate per call.

Meta's 34B Code Llama tuned for instruction following. A balance of size and quality for code generation, completion, and explanation, with strong coverage of Python, JavaScript, and other common languages. Runs on Replicate per call.

Meta's largest Code Llama, a 70B Llama-2 derivative specialized for programming and tuned to follow instructions in chat form. Handles code generation, completion, and explanation across common languages. Served on Replicate as a per-call endpoint.

Meta's smallest Code Llama at 7B parameters, tuned for instruction following. The cheapest and fastest member of the family for quick code generation, completion, and infilling. Served on Replicate per call.

Robust face-restoration model using a transformer-based codebook prior. Handles severe degradation, occlusion, and old-photo restoration with adjustable fidelity-quality tradeoff.

350M autoregressive code generation model from Salesforce, the smallest of the original CodeGen family. The mono variant was further trained on Python so it is well suited for short Python completions and program synthesis from a natural-language or code prompt.

CogVideoX-5B from Tsinghua/Zhipu AI, an open 5B-parameter text-to-video diffusion transformer. Generates 6-second 720p clips with coherent motion and is widely used in research for its open weights and reproducibility.

Zhipu/Tsinghua's 5B open text-to-video model. 720x480 @ 8fps, 6s clips, image-to-video variant available.

Tsinghua CogVLM2 19B with Llama-3 8B base plus 11B vision expert. Strong document understanding and visual reasoning, 8k context.

Open-weights multilingual research model from Cohere covering 23 languages. 35B parameters.

Cohere's fast lightweight chat model (deprecated Sep 2025). Kept as comparison tombstone.

Cohere's mid-tier RAG/tool model. Cost-efficient sibling of Command R+ with 128k context.

Cohere's flagship RAG- and tool-optimized chat model. 128k context, refreshed August 2024.

Cohere's multilingual embedding model. Supports 100+ languages with separate search and classification modes.

fofr's model generates the same character in many poses and angles from one reference image. Useful for building an avatar set or character sheet where the face and design stay consistent across outputs. Can produce a grid or individual images.

ControlNet conditioned on Canny edge maps. Preserves composition and outlines while restyling with Stable Diffusion 1.5 or SDXL backbones.

ControlNet conditioned on depth maps. Preserves the 3D scene layout while letting the prompt change style, lighting and content.

OpenAI's latest image generation model. Excellent at following complex prompts with high fidelity.

DDColor by Xiaoyang Kang et al. colorizes black-and-white photos using dual decoders that jointly learn pixel colors and semantic color queries, giving vivid and natural results on old images.

Deepgram's flagship STT. First to offer realtime multilingual transcription with self-serve customization.

1.3B instruction-tuned code model from DeepSeek, trained on 2 trillion tokens of code and natural language across 87 languages with a 16k context window. One of the strongest tiny coders for its size, handling generation, completion and short coding instructions.

Quantized GGUF build of DeepSeek's 33B code model, trained on roughly 2T tokens that are about 87 percent code. Designed for repository-level completion and project-aware generation thanks to a 16k context window. Runs on Replicate as a per-call endpoint.

DeepSeek's specialized coding model. Excellent at code generation, debugging, and explanation.

DeepSeek's reasoning model with chain-of-thought capabilities. Excellent for complex problem-solving.

Powerful open-weight model from DeepSeek. Strong at coding, math, and Chinese/English tasks.

Efficiency-optimized variant of DeepSeek V4. 284B MoE / 13B active, 1M context, ultra-low pricing for high-throughput workloads.

DeepSeek-VL 7B chat model. Vision-language model with hybrid vision encoder and strong real-world visual question answering performance.

DINOv2-base backbone fine-tuned for skin-disease image classification across 31 conditions, including basal cell carcinoma, lichen planus, lupus, herpes simplex, impetigo, leprosy variants and several genodermatoses. Broader than melanoma-only models. Research and educational use only, not a diagnostic.

Naver CLOVA Donut OCR-free document-understanding transformer. End-to-end JSON extraction from forms, receipts and invoices without explicit OCR.

Rednote Hilab Dots OCR. End-to-end document parsing model with layout, text and reading-order prediction in one transformer.

Generative Gaussian-splatting model for fast image-to-3D synthesis. Produces textured meshes in two minutes via differentiable rasterization.

Tencent DynamiCrafter. Animates still images into short videos preserving texture and structure, with strong open-domain coverage.

JaidedAI EasyOCR. Simple Python OCR wrapper supporting 80+ languages with deep-learning text detection and recognition.

Ant Group EchoMimic. Lifelike audio-driven portrait animation with editable landmark conditioning for fine-grained motion control.

Try-on pipeline aimed at ecommerce listings. You give it a photo containing clothing on a body pose plus a separate face image; it composes a person wearing that clothing with the supplied face, controllable by prompt, CFG, and output size. Useful for generating on-model product shots from a flat garment image.

Microsoft Edge neural voices accessed via the open-source edge-tts wrapper. 400+ voices across 100+ locales, suitable for batch generation.

Enhanced Super-Resolution GAN, the original 2018 architecture. Produces sharp 4x upscales with strong perceptual quality on natural images.

Open-source flow-matching TTS with strong zero-shot voice cloning. Code MIT, weights CC-BY-NC.

F5-TTS, a flow-matching TTS that clones a voice from a reference clip plus its transcript and reads new text in that voice. Fast non-autoregressive synthesis with optional silence removal.

fofr's face stylizer converts a face photo into 3D render, emoji, pixel art, video-game character, claymation or toy styles. Uses InstantID plus style LoRAs on SDXL to keep the likeness while applying a chosen art style. Popular for fun avatars.

fofr's model turns a face photo into a die-cut sticker with a white border and transparent background. Uses InstantID to hold the likeness and outputs a clean PNG suitable for chat stickers or print. Simple single-image input.

Google FILM frame interpolation. Synthesizes high-quality intermediate frames between near-duplicate inputs, designed for large motion gaps.

Microsoft Florence-2 Large. Unified prompt-based vision foundation model for captioning, detection, segmentation and OCR with a single 770M-param backbone.

Microsoft Florence-2 unified vision model with referring expression segmentation. Text-prompted region and mask generation in one model.

PuLID identity customization running on FLUX.1-dev. Inserts a face from one reference photo into prompt-driven scenes using contrastive alignment, giving higher likeness and detail than SDXL-era ID adapters. Good for realistic avatars and character portraits.

The fastest Flux model. Generate images in under 2 seconds. Great for prototyping.

The open-weight 12B rectified-flow transformer from Black Forest Labs. Close to FLUX Pro quality with a guidance-distilled checkpoint released under a non-commercial license. The most widely fine-tuned base in the FLUX family.

The fastest FLUX model from Black Forest Labs, distilled to produce images in 1 to 4 steps. Apache 2.0 licensed for commercial use. Built for high-volume generation and real-time previews.

Black Forest Labs' fastest open-weights image model. Apache-2.0 licensed, ~1-4 step inference.

FLUX structural control via Canny edge maps. Preserve composition while restyling.

Open-weight edge-guided FLUX model from Black Forest Labs. Extracts Canny edges from a control image and regenerates it from your prompt while holding the original composition and outlines, so you can restyle a scene without changing its structure.

FLUX structural control via depth maps. Keep 3D scene layout while changing style/content.

Open-weight depth-guided FLUX model from Black Forest Labs. Derives a depth map from the control image and regenerates from your prompt while preserving 3D spatial layout, useful for re-texturing rooms, products, or scenes without moving objects.

Black Forest Labs' inpainting/outpainting model for FLUX. Fill masked regions with prompt-guided content.

Black Forest Labs' open-weight inpainting and outpainting model, guidance-distilled from FLUX.1 Fill [pro]. You supply an image plus a mask and a prompt; it fills the masked region or extends the canvas with prompt-guided content that matches lighting and texture.

Open-weight version of FLUX.1 Kontext by Black Forest Labs. Instruction-based editing: pass an input image and a plain text edit ('change the jacket to red', 'remove the person on the left') and it applies the change while keeping the rest of the scene and identity consistent.

FLUX image-variation adapter. Generate variations and remixes from a reference image.

FLUX.1-dev inpainting wrapper that fills masked parts of an image from a prompt. Useful when you want FLUX-quality fills with a simple image plus mask plus prompt interface and adjustable mask strength.

Google Gemini 1.5 Flash, the fast low-cost multimodal model. 1M-token context, image/audio/video input, good for high-volume captioning, classification and long-video skim tasks.

Google DeepMind's vision-language-action model based on Gemini 2.0. Generalist robot policy with strong dexterity.

Embodied-reasoning variant of Gemini Robotics. Enhanced 3D spatial reasoning and trajectory planning.

NVIDIA GET3D generative model for textured 3D shapes. Trained on category-specific datasets producing meshes with high-quality textures.

Tencent ARC face-restoration GAN. Reconstructs realistic facial detail in low-quality or compressed photos using a pretrained StyleGAN2 prior.

Global-Local Path Networks depth-estimation model. Combines hierarchical transformer encoder with selective feature fusion for sharp boundaries.

Google's VLA from RT-X collaboration. Trained on Open-X-Embodiment (22 robots, 527 skills), positive transfer.

Faster cheaper Veo 3 with audio

Faster Veo 3.1 with image-to-video and audio

StepFun GOT-OCR 2.0. Unified end-to-end OCR-2.0 model handling text, formulas, charts, sheet music and geometric shapes in one architecture.

Small, fast, and affordable model for lightweight tasks. Great balance of speed and capability.

OpenAI's small multimodal model with image input. Much cheaper than GPT-4o, 128k context, good for high-volume captioning, OCR-style reads, tagging and screenshot understanding.

Smaller, faster, cheaper member of OpenAI's GPT-5 family. Tuned for high-throughput chat, classification and extraction where the full flagship is overkill.

OpenAI GPT-5.1 chat model (November 2025). An earlier GPT-5 point release kept available for compatibility. Good general-purpose reasoning and coding.

OpenAI's smallest and cheapest GPT-5.4 variant. Built for high-volume classification, extraction and coding subagents at edge-grade latency.

IBM Granite 20B Code Instruct. Larger Granite code model balancing quality and inference cost for enterprise CI/CD code-review automation.

IBM Granite 8B Code Instruct. Trained on permissively-licensed code, strong on multi-language code completion and instruction-following.

xAI's vision-capable Grok 2 snapshot. Image-in, text-out with strong multilingual instruction following.

xAI's flagship model. Strong at reasoning, coding, and real-time knowledge with web search capabilities.

xAI's cost-efficient high-throughput model. 2M context, optional reasoning, optimized for agentic loops and real-time apps.

xAI's Grok 4.20 standard snapshot. Skips the extended thinking pass for lower-latency answers on tasks that do not need deep deliberation. 1M token context window.

xAI's Grok 4.20 multi-agent snapshot. Coordinates several specialized agents under one call to handle multi-step workflows that mix research, tool use and synthesis. 1M token context window.

xAI's Grok coding-focused model. Tuned for code generation and software development tasks with a 256k token context window for working over large codebases.

xAI video with native audio and lip-sync, up to 15s

Grounding DINO plus SAM. Open-vocabulary text-prompted detection and segmentation in one pipeline for fully-automatic mask generation.

Alibaba (Tongyi Lab) general text embedding model. The v1.5 release extends the context to 8192 tokens and returns 1024-dim vectors, scoring competitively on MTEB while handling much longer inputs than typical 512-token encoders. A practical open model when documents exceed the usual short-context limit.

MiniMax's Hailuo video-01. 6s 1280x720 clips with strong cinematic motion and physical realism.

Minimax model for realistic human motion and VFX

Tencent's Hunyuan3D 2.0 image-to-3D pipeline. Two-stage shape and texture generation producing high-resolution textured meshes.

Refreshed Hunyuan3D 2.1 with improved texture fidelity and PBR-material support. Image-to-3D with textured GLB output.

Tencent's 13B open-weights video diffusion transformer. SOTA among open video models at release.

Lvmin Zhang's IC-Light packaged by zsxkib. Relights a product or portrait from a text prompt or a chosen light direction while keeping the subject's shape and detail intact, so a flat product photo can be given studio, window, or dramatic side lighting without re-shooting.

Hugging Face Idefics3 8B. Llama-3 based open-source vision-language model with strong document QA and chart-understanding performance.

Ideogram's fast text-to-image variant. Strong typography and logo rendering at low latency.

Ideogram's text-to-image model known for accurate in-image text and typography. Handles posters, logos, and signage where other models garble lettering. Supports magic prompt expansion and multiple aspect ratios.

Ideogram's fast v3 model, the fastest and cheapest tier of the v3 family. Known for accurate in-image text rendering and reliable typography, which most diffusion models still get wrong. Hosted API only.

IDM-VTON virtual try-on from the CVPR 2024 paper. You give it a photo of a person and a garment image; it dresses the person in that garment while preserving pose, body shape, and the garment's pattern and text. Good for showing a clothing product on a model for an ecommerce listing.

Image-to-3D mesh generator from sparse-view diffusion. Produces textured meshes in under one minute on a single A100.

Berkeley InstructPix2Pix. Edits an image from natural-language instructions in a single forward pass. Trained on GPT-3 plus Stable Diffusion synthetic pairs.

Tencent's face-identity conditioning adapter for SD/SDXL. Face embedding + CLIP for ID-consistent generation.

DeepSeek's unified multimodal model. Decouples vision encoding for both understanding and generation tasks.

Jina's frontier multilingual embedding model. 570M params, 8192 ctx, 89 languages, Matryoshka dims 128-1024.

Kuaishou's Kling 1.6 Pro. Premium cinematic motion and physics realism, ~$0.07/sec.