Loading…
CRAISEE · Oct 24, 2026
Accelerated inference for Wan 2.1 14B image to video, a comprehensive and open suite of video foundation models that pushes the boundaries of video generation.
CRAISEE · Oct 23, 2026
A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality
CRAISEE · Oct 22, 2026
PixVerse's highest-quality video model. Generate up to 15 seconds of 1080p video with synchronized audio, from text or an image.
CRAISEE · Oct 21, 2026
An enhanced version over Qwen-Image-Edit-2509, featuring multiple improvements including notably better consistency
CRAISEE · Oct 20, 2026
Create 5s-8s videos with enhanced character movement, visual effects, and exclusive 1080p-8s support. Optimized for anime characters and complex actions
CRAISEE · Oct 16, 2026
OpenAI's new model excelling at coding, writing, and reasoning.
CRAISEE · Oct 15, 2026
Fastest, most cost-effective GPT-4.1 model from OpenAI
CRAISEE · Oct 13, 2026
Fast, affordable version of GPT-4.1
CRAISEE · Oct 11, 2026
An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.
CRAISEE · Oct 10, 2026
Kling 2.5 Turbo Pro: Unlock pro-level text-to-video and image-to-video creation with smooth motion, cinematic depth, and remarkable prompt adherence.
CRAISEE · Oct 8, 2026
Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty
CRAISEE · Oct 5, 2026
Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge
CRAISEE · Oct 4, 2026
A sub 1 second text-to-image model built for production use cases.
CRAISEE · Oct 2, 2026
A 17 billion parameter model with 16 experts
CRAISEE · Sep 30, 2026
Fastest, most cost-effective GPT-5 model from OpenAI
CRAISEE · Sep 29, 2026
A very fast and cheap PrunaAI optimized version of Wan 2.2 A14B image-to-video
CRAISEE · Sep 27, 2026
This is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
CRAISEE · Sep 26, 2026
Complete guide to using video-utils on CRAISEE.
CRAISEE · Sep 25, 2026
A sub 1 second 0.01$ multi-image editing model built for production use cases. For image generation, check out p-image here: https://replicate.com/prunaai/p-image
CRAISEE · Sep 24, 2026
Google's state of the art image generation and editing model 🍌🍌
CRAISEE · Sep 23, 2026
Z-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
CRAISEE · Sep 23, 2026
Google's latest image editing model in Gemini 2.5
CRAISEE · Apr 25, 2026
ltx-2.3-fast: Lightricks' 22B-parameter distilled DiT model generating 4K/50FPS clips up to 20s in 8 steps. Full deployment, prompting & benchmarks inside.
CRAISEE · Apr 25, 2026
A 17 billion parameter model with 128 experts
CRAISEE · Apr 25, 2026
Learn what lipsync-speed does, how it works, and when to use it. Includes best prompts, sync modes, and pipeline tips for fast dubbing workflows.
CRAISEE · Apr 25, 2026
lipsync-2-pro by Sync Labs: 4K diffusion-enhanced AI lip sync model. Full 2025–2026 guide covering architecture, API integrations, and deployment for production teams.
CRAISEE · Apr 25, 2026
Master heygen/lipsync-precision: architecture deep-dive, input parameters, and deployment tips for HeyGen's top-quality AI lip-sync model on Replicate (2025).
CRAISEE · Apr 25, 2026
Learn how lipsync-2 by Sync Labs works: zero-shot lip sync, chunk-based architecture, $0.04/sec pricing, best prompts, and when to upgrade to sync-3.
CRAISEE · Apr 25, 2026
Compare top AI lipsync models—sync-3, VEED Fabric, MuseTalk—with exact pricing, failure modes, and input tips for dubbing, avatars, and real-time agents.
CRAISEE · Apr 25, 2026
Kling v3 is Kuaishou's #1-ranked AI video model (ELO 1243). Learn its MVL architecture, 4K specs, pricing, and prompt strategy in this complete guide.
CRAISEE · Apr 25, 2026
Complete guide to kling-v3-omni-video (Kling 3.0 Omni): architecture, benchmarks, input modes, and API usage for the top-rated AI video model of 2026.
CRAISEE · Apr 25, 2026
Kling v3 Motion Control (kling-v3-motion-control): the #1 ELO-ranked AI video model for reference-video motion transfer. Full technical guide—config, benchmarks, and deployment tips.
CRAISEE · Apr 25, 2026
Kling v2.6 generates video, voice, and audio in one pass. Learn its architecture, pricing, prompt tips, and how it compares to rivals—then try it on CRAISEE.
CRAISEE · Apr 25, 2026
Kling O1 unifies video generation, editing & refinement in one engine. Learn its architecture, capabilities, output specs, and expert prompting tips.
CRAISEE · Apr 25, 2026
Complete reference guide to Kling Lip Sync: architecture, zero-shot speaker adaptation, input formats, costs, and prompt formulas for production-ready facial animation.
CRAISEE · Apr 25, 2026
kling-avatar-v2 turns a single image into lip-synced video at 1080p/48fps. Full guide: specs, pricing, prompting tips, and API usage for developers and creators.
CRAISEE · Apr 25, 2026
Kimi K2.5: 1T-parameter sparse MoE model by Moonshot AI. Explore architecture, benchmarks, pricing across 14 providers, and mode-selection tips in this technical guide.
CRAISEE · Apr 25, 2026
Use this ultra version of Imagen 4 when quality matters more than speed and cost
CRAISEE · Apr 25, 2026
Kimi K2 Thinking: 1T-parameter open-weights reasoning model by Moonshot AI. Covers architecture, benchmarks, pricing, limits & prompt patterns for agentic AI.
CRAISEE · Apr 25, 2026
Use this fast version of Imagen 4 when speed and cost are more important than quality
CRAISEE · Apr 25, 2026
Learn how AI image upscale models work, compare GAN vs. diffusion architectures, and get the best prompts for 4K-ready results — with CRAISEE.
CRAISEE · Apr 25, 2026
Google's Imagen 4 flagship model
CRAISEE · Apr 25, 2026
Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
CRAISEE · Apr 25, 2026
Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles
CRAISEE · Apr 25, 2026
The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles
CRAISEE · Apr 25, 2026
Generate consistent characters from a single reference image. Outputs can be in many styles. You can also use inpainting to add your character to an existing image.
CRAISEE · Apr 25, 2026
A powerful native multimodal model for image generation (PrunaAI squeezed)
CRAISEE · Apr 25, 2026
Generate high-quality 2K resolution images from text prompts
CRAISEE · Apr 25, 2026
3D models with texture fidelity and geometry precision
CRAISEE · Apr 25, 2026
A lower-latency image-to-video version of Hailuo 2.3 that preserves core motion quality, visual consistency, and stylization performance while enabling faster iteration cycles.
CRAISEE · Apr 25, 2026
A high-fidelity video generation model optimized for realistic human motion, cinematic VFX, expressive characters, and strong prompt and style adherence across both text-to-video and image-to-video workflows
CRAISEE · Apr 25, 2026
Extend videos with xAI's Grok Imagine Video model. Provide a source video and describe what happens next.
CRAISEE · Apr 25, 2026
Generate videos using xAI's Grok Imagine Video model
CRAISEE · Apr 25, 2026
Generate videos guided by reference images using xAI's Grok Imagine Video model
CRAISEE · Apr 25, 2026
SOTA image model from xAI
CRAISEE · Apr 25, 2026
Granite-speech-3.3-8b is a compact and efficient speech-language model, specifically designed for automatic speech recognition (ASR) and automatic speech translation (AST).
CRAISEE · Apr 25, 2026
Deprecated: This model has been replaced by xai/grok-imagine-image. The upstream grok-2-image-1212 model was deprecated by xAI on February 24, 2026.
CRAISEE · Apr 25, 2026
Granite-4.0-H-Small is a 32B parameter long-context instruct model finetuned from Granite-4.0-H-Small-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets.
CRAISEE · Apr 25, 2026
Join the Granite community where you can find numerous recipe workbooks to help you get started with a wide variety of use cases using this model. https://github.com/ibm-granite-community
CRAISEE · Apr 25, 2026
120b open-weight language model from OpenAI
CRAISEE · Apr 25, 2026
OpenAI's latest image generation model with better instruction following and adherence to prompts
CRAISEE · Apr 25, 2026
Faster version of OpenAI's flagship GPT-5 model
CRAISEE · Apr 25, 2026
A speech-to-text model that uses GPT-4o to transcribe audio
CRAISEE · Apr 25, 2026
A speech-to-text model that uses GPT-4o mini to transcribe audio
CRAISEE · Apr 25, 2026
OpenAI's high-intelligence chat model
CRAISEE · Apr 25, 2026
Bria Background Generation allows for efficient swapping of backgrounds in images via text prompts or reference image, delivering realistic and polished results. Trained exclusively on licensed data for safe and risk-free commercial use
CRAISEE · Apr 25, 2026
State-of-the-art video motion quality, prompt adherence and visual fidelity
CRAISEE · Apr 25, 2026
Google's most intelligent model, with improved reasoning and a new medium thinking level
CRAISEE · Apr 25, 2026
Google's fast, expressive text-to-speech model with 30 voices and 70+ language support
CRAISEE · Apr 25, 2026
Google's most advanced reasoning Gemini model
CRAISEE · Apr 25, 2026
Google's latest image generation model in Gemini 2.5
CRAISEE · Apr 25, 2026
Google’s hybrid “thinking” AI model optimized for speed and cost-efficiency
CRAISEE · Apr 25, 2026
A state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
CRAISEE · Apr 25, 2026
A premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
CRAISEE · Apr 25, 2026
Professional depth-aware image generation. Edit images while preserving spatial relationships.
CRAISEE · Apr 25, 2026
High-quality image generation and editing with support for eight reference images
CRAISEE · Apr 25, 2026
Open-weight depth-aware image generation. Edit images while preserving spatial relationships.
CRAISEE · Apr 25, 2026
The highest fidelity image model from Black Forest Labs
CRAISEE · Apr 25, 2026
4 step distilled version of FLUX.2 [klein]. A foundation model for maximum flexibility and control
CRAISEE · Apr 25, 2026
Very fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.
CRAISEE · Apr 25, 2026
Max-quality image generation and editing with support for ten reference images
CRAISEE · Apr 25, 2026
Quality image generation and editing with support for reference images
CRAISEE · Apr 25, 2026
A step-distilled version of flux 2 down to 1s.
CRAISEE · Apr 25, 2026
ElevenLabs's fastest speech synthesis model
CRAISEE · Apr 25, 2026
Bria Expand expands images beyond their borders in high quality. Resizing the image by generating new pixels to expand to the desired aspect ratio. Trained exclusively on licensed data for safe and risk-free commercial use
CRAISEE · Apr 25, 2026
SOTA Object removal, enables precise removal of unwanted objects from images while maintaining high-quality outputs. Trained exclusively on licensed data for safe and risk-free commercial use
CRAISEE · Apr 25, 2026
4MP text-to-image generation with enhanced cinematic-quality image generation with precise style control, improved text rendering, and commercial design optimization.
CRAISEE · Apr 25, 2026
Monocular metric depth estimation
CRAISEE · Apr 25, 2026
Animate any character, humans, cartoons, animals, even non-humans, from a single image + driving video
CRAISEE · Apr 25, 2026
Latest hybrid thinking model from Deepseek
CRAISEE · Apr 25, 2026
A reasoning model trained with reinforcement learning, on par with OpenAI o1
CRAISEE · Apr 25, 2026
High-precision video upscaler optimized for portraits, faces and products. One of the upscale modes powered by Clarity AI. X:https://x.com/philz1337x
CRAISEE · Apr 25, 2026
Anthropic's most capable model with a step-change improvement in agentic coding, better vision, and stronger multi-step reasoning
CRAISEE · Apr 25, 2026
Top-tier reasoning and multilingual
CRAISEE · Apr 25, 2026
Newest MiniMax flagship model
CRAISEE · Apr 25, 2026
Recent balanced MiniMax model
CRAISEE · Apr 25, 2026
Balanced open model
CRAISEE · Apr 25, 2026
Largest open-weight model
CRAISEE · Apr 25, 2026
State-of-the-art image generation
CRAISEE · Apr 25, 2026
Reasoning-enabled Grok variant
CRAISEE · Apr 25, 2026
Low-latency Grok variant
CRAISEE · Apr 25, 2026
Professional video generation
CRAISEE · Apr 25, 2026
Fast Gemini 3.1 model
CRAISEE · Apr 25, 2026
Low-cost Gemini 2.5 text model
CRAISEE · Apr 25, 2026
Newest fast OpenAI model
CRAISEE · Apr 25, 2026
OpenAI coding-specialized model
CRAISEE · Apr 25, 2026
Fast and efficient model for everyday tasks
CRAISEE · Apr 25, 2026
Most capable OpenAI model for complex tasks
CRAISEE · Apr 25, 2026
Recent general-purpose Z.ai model
CRAISEE · Apr 25, 2026
Natural speech synthesis
CRAISEE · Apr 25, 2026
Latest DeepSeek text model
CRAISEE · Apr 25, 2026
Optimized for code generation
CRAISEE · Apr 25, 2026
Newest balanced Anthropic model
CRAISEE · Apr 25, 2026
Reliable Sonnet generation
CRAISEE · Apr 25, 2026
Previous-gen Anthropic flagship
CRAISEE · Apr 25, 2026
Fast Anthropic text model
