Pick a model. Type a prompt. Get a result.
Explore available models
Start with these #
BORROW THE STYLE
GPT Image 2.5 Sunburst
Precise professional edits, detailed image control, and sharp text rendering.
Illustrate a sculptural cobalt blue glass vase holding a single orange tulip. Contemporary editorial gouache illustration with cut-paper shapes, subtle risograph grain, warm ivory, cobalt blue, moss green and burnt orange, tactile matte surfaces, soft afternoon light, generous negative space, elegant playful composition. Portrait 3:4 composition. No text, lettering, logo or watermark.
A few of the image models you can use.
See all models 56
Handpicked AI models for generating text, image, video, voice and music.. #
## Text10 #
Write, reason, and analyze with the right mind for the task.
Gemini 3.1 Pro NEWGoogle #
Advanced multimodal reasoning with low, medium, and high thinking levels.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/google/gemini-3.1-pro)
## [Qwen3.7 Plus NEW](https://supermodels.phototypelabs.com/text?model=replicate/qwen/qwen3-7-plus)Alibaba
Multimodal reasoning and coding with vision-language understanding.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/qwen/qwen3-7-plus)
## [GPT-5.6 Sol NEW](https://supermodels.phototypelabs.com/text?model=replicate/openai/gpt-5.6-sol)OpenAI
OpenAI flagship for deep multi-step reasoning and professional coding.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/openai/gpt-5.6-sol)
## [Claude Fable 5 NEW](https://supermodels.phototypelabs.com/text?model=replicate/anthropic/claude-fable-5)Anthropic
Next-generation Anthropic model for demanding knowledge work and coding.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/anthropic/claude-fable-5)
## [Claude Sonnet 5 NEW](https://supermodels.phototypelabs.com/text?model=replicate/anthropic/claude-sonnet-5)Anthropic
Fast frontier-level coding and agentic work.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/anthropic/claude-sonnet-5)
## [Gemini 3.5 Flash NEW](https://supermodels.phototypelabs.com/text?model=replicate/google/gemini-3.5-flash)Google
Fast multimodal frontier reasoning for agents, code, and long-context work.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/google/gemini-3.5-flash)
## [GPT-5.6 Terra NEW](https://supermodels.phototypelabs.com/text?model=replicate/openai/gpt-5.6-terra)OpenAI
Balanced GPT-5.6 production tier for everyday work.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/openai/gpt-5.6-terra)
## [GPT-5.6 Luna NEW](https://supermodels.phototypelabs.com/text?model=replicate/openai/gpt-5.6-luna)OpenAI
Cost-optimized GPT-5.6 tier for high-volume, latency-sensitive tasks.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/openai/gpt-5.6-luna)
## [Claude 4.5 Haiku](https://supermodels.phototypelabs.com/text?model=replicate/anthropic/claude-4.5-haiku) Anthropic
Very fast responses with strong instruction following.
[Open text workspace](https://supermodels.phototypelabs.com/text?model=replicate/anthropic/claude-4.5-haiku)
## [Gemma 2B IT](https://supermodels.phototypelabs.com/text?model=replicate/google-deepmind/gemma-2b-it) Google
Compact open model for quick lightweight tasks.
## Image20 #
Create, edit, and refine still imagery.
GPT Image 2.5 Flare NEWOpenAI #
Fast, high-quality everyday image generation, text rendering, and edits.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/openai/gpt-image-2.5-flare)
## [GPT Image 2.5 Sunburst NEW](https://supermodels.phototypelabs.com/image?model=replicate/openai/gpt-image-2.5-sunburst)OpenAI
Precise professional edits, detailed image control, and sharp text rendering.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/openai/gpt-image-2.5-sunburst)
## [FLUX 3 Image NEW](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-3-image)Black Forest Labs
FLUX 3 is Black Forest Labs' text-to-image and image-editing model. Generate images from a prompt, or edit with up to 10 reference images.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-3-image)
## [Qwen Image 3 NEW](https://supermodels.phototypelabs.com/image?model=replicate/alibaba/qwen-image-3)Alibaba
Qwen-Image-3.0 generates and edits images with accurate text rendering, complex layouts, and photographic detail.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/alibaba/qwen-image-3)
## [Qwen Image 3 Pro NEW](https://supermodels.phototypelabs.com/image?model=replicate/alibaba/qwen-image-3-pro)Alibaba
Qwen-Image-3.0-Pro generates and edits images with dense, accurate text rendering, complex multi-element layouts, and photographic detail.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/alibaba/qwen-image-3-pro)
## [Qwen Image Layered NEW](https://supermodels.phototypelabs.com/image?model=replicate/qwen/qwen-image-layered)Alibaba
Generate images with separate foreground, background, and shadow layers for easy editing and compositing
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/qwen/qwen-image-layered)
## [Qwen Edit Multiangle NEW](https://supermodels.phototypelabs.com/image?model=replicate/qwen/qwen-edit-multiangle)Alibaba
Camera-aware edits for Qwen/Qwen-Image-Edit-2509 with Lightning + multi-angle LoRA
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/qwen/qwen-edit-multiangle)
## [Nano Banana Pro](https://supermodels.phototypelabs.com/image?model=replicate/google/nano-banana-pro) Google
Complex layouts, multi-image blends, and text-heavy campaign compositions.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/google/nano-banana-pro)
## [Nano Banana 2 Lite](https://supermodels.phototypelabs.com/image?model=replicate/google/nano-banana-2-lite) Google
Low-cost rapid drafts, conversational edits, and high-volume visual exploration.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/google/nano-banana-2-lite)
## [FLUX.2 Max](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-2-max) Black Forest Labs
Premium product shots, fashion imagery, and highest-fidelity photoreal scenes.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-2-max)
## [FLUX.2 Pro](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-2-pro) Black Forest Labs
Client-ready photoreal imagery with strong polish at a practical cost.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-2-pro)
## [Seedream 4.5](https://supermodels.phototypelabs.com/image?model=replicate/bytedance/seedream-4.5) ByteDance
Cinematic scenes, richer world detail, and stronger spatial compositions.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/bytedance/seedream-4.5)
## [Seedream 5.0 Pro](https://supermodels.phototypelabs.com/image?model=replicate/bytedance/seedream-5-pro) ByteDance
Structured visuals, precise typography, photoreal imagery, and multi-reference edits.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/bytedance/seedream-5-pro)
## [FLUX Schnell](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-schnell) Black Forest Labs
Fastest ideation model for rough options, moodboards, and batch exploration.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/black-forest-labs/flux-schnell)
## [Grok Imagine Image](https://supermodels.phototypelabs.com/image?model=replicate/xai/grok-imagine-image) xAI
Fast image generation and editing with strong creative control and text rendering.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/xai/grok-imagine-image)
## [Grok Imagine Image Quality (Legacy)](https://supermodels.phototypelabs.com/image?model=replicate/xai/grok-imagine-image-quality) xAI
Legacy high-fidelity image model. xAI schedules this model slug for retirement on November 2, 2026; use Grok Imagine Image 2.0 for continued support.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/xai/grok-imagine-image-quality)
## [Grok Imagine Image 2.0](https://supermodels.phototypelabs.com/image?model=replicate/xai/grok-imagine-image-2) xAI
Latest Grok Imagine image model with generation and editing, quality control, and output up to 2K.
[Open image workspace](https://supermodels.phototypelabs.com/image?model=replicate/xai/grok-imagine-image-2)
## [P-Image Upscale](https://supermodels.phototypelabs.com/gallery?model=replicate/prunaai/p-image-upscale) PrunaAI
Very fast upscales with target-megapixel or factor-based sizing.
[Open gallery](https://supermodels.phototypelabs.com/gallery?model=replicate/prunaai/p-image-upscale)
## [Clarity Pro Upscaler](https://supermodels.phototypelabs.com/gallery?model=replicate/philz1337x/clarity-pro-upscaler) Clarity AI
Photorealistic upscales with strict-to-creative detail control.
[Open gallery](https://supermodels.phototypelabs.com/gallery?model=replicate/philz1337x/clarity-pro-upscaler)
## [Topaz Image Upscale](https://supermodels.phototypelabs.com/gallery?model=replicate/topazlabs/image-upscale) Topaz Labs
Professional-grade image upscaling with model-specific enhancement and face controls.
## Voice5 #
Give scripts a distinctive sound.
Qwen3 TTS NEWAlibaba #
A unified Text-to-Speech demo featuring three powerful modes: Voice, Clone and Design
[Open voice workspace](https://supermodels.phototypelabs.com/voice?model=replicate/qwen/qwen3-tts)
## [Eleven Turbo v2.5 NEW](https://supermodels.phototypelabs.com/voice?model=replicate/elevenlabs/turbo-v2.5)ElevenLabs
High quality, low latency text to speech in 32 languages
[Open voice workspace](https://supermodels.phototypelabs.com/voice?model=replicate/elevenlabs/turbo-v2.5)
## [Gemini 3.1 Flash TTS](https://supermodels.phototypelabs.com/voice?model=replicate/google/gemini-3.1-flash-tts) Google
Fast multilingual TTS with 30 voices, style prompting, and inline delivery tags.
[Open voice workspace](https://supermodels.phototypelabs.com/voice?model=replicate/google/gemini-3.1-flash-tts)
## [Eleven v3](https://supermodels.phototypelabs.com/voice?model=replicate/elevenlabs/v3) ElevenLabs
Highly expressive single-speaker voiceovers with audio tags and context controls.
[Open voice workspace](https://supermodels.phototypelabs.com/voice?model=replicate/elevenlabs/v3)
## [Grok Text-to-Speech](https://supermodels.phototypelabs.com/voice?model=replicate/xai/grok-text-to-speech) xAI
Expressive speech synthesis with five voices, language selection, and MP3, WAV, PCM, and telephony output.
## Music3 #
Compose clips, soundtracks, and full songs.
Lyria 3 Pro NEWGoogle #
Generate full-length songs up to 3 minutes from text prompts or images with Lyria 3 Pro, Google's most capable music generation model
[Open music workspace](https://supermodels.phototypelabs.com/music?model=replicate/google/lyria-3-pro)
## [Lyria 3 NEW](https://supermodels.phototypelabs.com/music?model=replicate/google/lyria-3)Google
Generate 30-second music clips from text prompts or images with Lyria 3, Google's music generation model
[Open music workspace](https://supermodels.phototypelabs.com/music?model=replicate/google/lyria-3)
## [ElevenLabs Music NEW](https://supermodels.phototypelabs.com/music?model=replicate/elevenlabs/music)ElevenLabs
Compose a song from a prompt or a composition plan
## Video18 #
Move from a prompt or reference into motion.
FLUX 3 Video NEWBlack Forest Labs #
Generate short videos from text, image references, or a source video.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/black-forest-labs/flux-3)
## [Wan 3 NEW](https://supermodels.phototypelabs.com/video?model=replicate/alibaba/wan-3)Alibaba
Low-cost text-to-video or image-to-video drafts at 480p through 1080p.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/alibaba/wan-3)
## [Gemini Omni 1.1 NEW](https://supermodels.phototypelabs.com/video?model=replicate/google/gemini-omni-1.1)Google
Google's fast multimodal video generation and editing model with native audio, using the Interactions API
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/google/gemini-omni-1.1)
## [Veo 3.1 Lite NEW](https://supermodels.phototypelabs.com/video?model=replicate/google/veo-3.1-lite)Google
Google's cost-efficient video generation model with native audio, optimized for high-volume applications
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/google/veo-3.1-lite)
## [Veo 3.1 Fast NEW](https://supermodels.phototypelabs.com/video?model=replicate/google/veo-3.1-fast)Google
Fast high-fidelity video generation with context-aware audio and last-frame support
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/google/veo-3.1-fast)
## [Veo 3.1 NEW](https://supermodels.phototypelabs.com/video?model=replicate/google/veo-3.1)Google
High-fidelity video generation with context-aware audio, reference images, and last-frame support
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/google/veo-3.1)
## [Sora 2 Pro NEW](https://supermodels.phototypelabs.com/video?model=replicate/openai/sora-2-pro)OpenAI
OpenAI's Most advanced synced-audio video generation
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/openai/sora-2-pro)
## [FLUX Video Upscale NEW](https://supermodels.phototypelabs.com/video?model=replicate/black-forest-labs/flux-video-upscale)Black Forest Labs
Upscale videos to higher resolution with FLUX super-resolution. Precise mode sharpens and stays faithful to the source; creative mode restores and invents fine detail.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/black-forest-labs/flux-video-upscale)
## [Seedance 2.0 Mini NEW](https://supermodels.phototypelabs.com/video?model=replicate/bytedance/seedance-2.0-mini)ByteDance
A lower-cost variant of Seedance 2.0 for high-volume video generation with multimodal inputs and native audio.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/bytedance/seedance-2.0-mini)
## [ByteDance Video Upscaler NEW](https://supermodels.phototypelabs.com/video?model=replicate/bytedance/video-upscaler)ByteDance
Upscale and enhance video up to 4K at 60fps, with scene-aware presets for AI-generated content, short dramas, UGC, and film restoration.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/bytedance/video-upscaler)
## [Kling Avatar v2 NEW](https://supermodels.phototypelabs.com/video?model=replicate/kwaivgi/kling-avatar-v2)Kuaishou
Create avatar videos with realistic humans, animals, cartoons, or stylized characters
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/kwaivgi/kling-avatar-v2)
## [Wan 3 Prime NEW](https://supermodels.phototypelabs.com/video?model=replicate/alibaba/wan-3-prime)Alibaba
Generate videos from text prompts using Alibaba's Wan 3.0 Prime model. Up to 1080p and 30 seconds, with 480p, 720p, and 1080p output.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/alibaba/wan-3-prime)
## [Seedance 2.0 Fast](https://supermodels.phototypelabs.com/video?model=replicate/bytedance/seedance-2.0-fast) ByteDance
Fast multimodal drafts with audio, first/last frames, reference images, videos, and audio.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/bytedance/seedance-2.0-fast)
## [Kling v3 Motion Control](https://supermodels.phototypelabs.com/video?model=replicate/kwaivgi/kling-v3-motion-control) Kuaishou
Transfer a character’s movement from a source video to a reference image.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/kwaivgi/kling-v3-motion-control)
## [Grok Imagine Video](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-video) xAI
Text-to-video, image-to-video, and video editing with synchronized generated audio.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-video)
## [Grok Imagine Video 1.5 (Preview)](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-video-1.5) xAI
Preview image-to-video model with synchronized audio. Requires a source image.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-video-1.5)
## [Grok Imagine R2V](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-r2v) xAI
Reference-to-video generation guided by one to seven reference images.
[Open video workspace](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-r2v)
## [Grok Imagine Video Extension](https://supermodels.phototypelabs.com/video?model=replicate/xai/grok-imagine-video-extension) xAI
Continue an existing video with a prompt-guided extension.
Model providers. #
Pricing #
Choose a wallet top-up and the models you want to explore. Compare a typical shared budget with the maximum if you spent it all on one model.
$10
Choose an amount from the current $10 minimum up to $1,000.
0 / 0
—
Select models to estimate how far your wallet credit goes. All model workspaces are available to signed-in members. Batch image creation and image description are also available.
Estimates use each model’s default settings and current published prices. Actual prices can change with settings, references, duration, and usage; review the workspace estimate before creating.
OUR POV
Curated. Not crowded. #
We don't have all AI models, but rather cherry-pick the latest and greatest.
Everything you need, in one app. #
Write and analyze
Draft, summarize, and research with AI.
Open text workspace An open cream notebook on a cobalt blue writing desk, a moss green fountain pen and folded burnt orange paper sheets. Abstract flowing ink strokes rise from the notebook and become elegant paper ribbons, suggesting writing and thought. Pages have no readable letters or symbols. Contemporary editorial gouache illustration with cut-paper shapes and subtle risograph grain on warm ivory paper. Restricted palette of cobalt blue, moss green, burnt orange and cream. Tactile matte surfaces, deliberately simplified flat shapes, hand-painted edges, soft afternoon light, elegant playful composition with generous negative space. Clearly an illustration throughout, including every object: no photorealism, no 3D rendering, no glossy photographic reflections. Square composition, main subject centered with comfortable margins. No text, lettering, logo, watermark, borders or captions.
IMAGE MODELOpenAI imagegen
What you get #
Your tools, finally together.
Move from an image idea to a voiceover or soundtrack without juggling provider accounts. Compare models, switch direction, and keep your creative workflow in one familiar studio.
Know price before every generation.
Choose your model and settings, then see the estimated cost before you press Generate. Add wallet credit when a project needs it and spend it across models, at your own pace.
A private home for what you make.
Keep your images, voiceovers, and music together in your gallery. Return to a useful result, download it for your project, or choose what to feature publicly. Sharing is always your decision.
MADE FOR YOUR WORK
From a rough idea to your next deliverable. #
A campaign that needs a new direction. A pitch that needs a picture. A story that needs a voice. Find a starting point below, borrow the prompt, and make it your own.
Many providers, one place.
Explore image and voice tools from one workspace instead of managing another collection of tabs.
Choose for the brief.
Compare models and their capabilities, then pick the approach that suits the work.
Know before you create.
Check the estimated price for the selected model and settings before each run.
Create at your pace.
Add wallet credit when you need it and spend it on the creations you choose.
EXPLORE BY CATEGORY
Find your starting point.
Browse the examples, or choose a category to jump to its image.
FROM IDEA TO OUTPUT
How it works
- 01 / EXPLORE#### Find your starting point.Try the guest workspace, browse models, and save a draft in this browser.
- 02 / ACCOUNT#### Sign in and add credit.Create or sign in to an account with Google and add wallet credit when you are ready.
- 03 / CREATE#### Review, then create.Choose a model and settings, check the estimated price, and run your generation.
- 04 / KEEP#### Refine and decide what to share.Review or download your work in your private gallery; publish a profile only if you choose.
FROM THE STUDIO
The latest from Supermodels. #
All posts the latest posts…
Frequently asked question
FAQ #
What is Supermodels? #
Supermodels is all-in-one platform with a handpicked selection of the very best models from leading providers such as: OpenAI, Google, Anthropic, xAI, ByteDance, ElevenLabs and more…
Who is it for? #
It can help designers, small studios, architects exploring early concepts, brands, marketers, creators, and anyone who wants to choose among models for a specific project.
Which tools can I use today? #
Signed-in users can create with image, text, voice, music, and video models. Batch image creation and image description are also available in the workspace.
Can I try an idea before signing in? #
Yes. The guest workspace lets you draft image, batch, and voiceover ideas in your browser. Sign in with Google when you are ready to generate; drafts and reference files stay on this device beforehand.
How does pricing work? #
Add wallet credit when you need it, then check the estimated price for the model and settings before each image, voice, or music generation. Custom wallet top-ups start at $10; prices vary by model and settings.
Can I use reference images or edit an image? #
Some image models support reference images and edits. The model catalog and comparison show capabilities where they are available; controls differ by model.
Who can see my creations? #
Your work is private in your gallery by default. You can download it or choose to activate a public profile and feature selected assets. Soon.
How much storage is included? #
A paid wallet top-up unlocks the current included 1 GB storage allowance. The Settings page shows your current use.
What happens if an image generation fails? #
Image credit reserved for a failed generation is released back to your available balance.
Can I use generated assets commercially? #
Yes.
When will Business/Teams be available? #
Shared budgets and team workflows are coming soon, no specific launch date set yet. If you're interested, sign in to your profile and check the interest box if you would like to be the first to try when it becomes available.