Nano Banana Pro
Google · Image
ProText to image · Image edit · 4K
4 / imagePull
The 72 AI models on Pickshot: image, video and audio
Image, video and audio models stand in a row like capsule machines. Pick one, type a prompt, pull the lever.
Image
23 machinesNano Banana 2
Google · Image
Text to image · Image edit · 2K
2 / imagePull
Seedream 5.0 Pro
ByteDance · Image
NewText to image · Image edit · 4K
3 / imagePull
GPT Image 2.5
OpenAI · Image
NewText to image · Image edit · 2K
4 / imagePull
Z-Image Turbo
Alibaba Tongyi · Image
Open modelText to image
FreePull
Chroma
Lodestone · Image
Open modelText to image
1 / imagePull
WAI Illustrious
Community · Image
Open modelText to image
FreePull
GPT Image 2
OpenAI · Image
Text to image · Image edit · 2K
3 / imagePull
Qwen Image 3.0
Alibaba · Image
Text to image · Image edit
2 / imagePull
Wan 2.7 Image
Alibaba · Image
Text to image · Image edit
2 / imagePull
Kling V3 Image
Kuaishou · Image
Text to image · Image edit
2 / imagePull
Hunyuan Image 3.5
Tencent · Image
NewText to image · Image edit
2 / imagePull
Grok Imagine
xAI · Image
Text to image · Image edit
2 / imagePull
FLUX.2 Dev
Black Forest Labs · Image
Text to image · Image edit
3 / imagePull
FLUX.2 Klein 9B
Black Forest Labs · Image
Text to image · Image edit
1 / imagePull
FLUX.2 Klein 4B
Black Forest Labs · Image
FastText to image · Image edit
FreePull
Krea 2 Turbo
Krea · Image
Open modelText to image
1 / imagePull
HiDream I1
HiDream.ai · Image
Open modelText to image
1 / imagePull
Stable Diffusion 3.5 Large
Stability AI · Image
Open modelText to image
1 / imagePull
SDXL
Stability AI · Image
Open modelText to image
FreePull
Pony Diffusion
Community · Image
Open modelText to image
FreePull
Phoenix 1.0
Leonardo.Ai · Image
Text to image
2 / imagePull
Lucid Origin
Leonardo.Ai · Image
Text to image
2 / imagePull
| Model | How to make it | Length · Resolution | Credits / image |
|---|---|---|---|
Nano Banana Pro Google | Text to image, Image edit | 1K / 2K / 4K | 4 / image |
Nano Banana 2 Google | Text to image, Image edit | 1K / 2K | 2 / image |
Seedream 5.0 Pro ByteDance | Text to image, Image edit | 2K / 4K | 3 / image |
GPT Image 2 OpenAI | Text to image, Image edit | 1K / 2K | 3 / image |
GPT Image 2.5 OpenAI | Text to image, Image edit | 1K / 2K | 4 / image |
Qwen Image 3.0 Alibaba | Text to image, Image edit | — | 2 / image |
Wan 2.7 Image Alibaba | Text to image, Image edit | — | 2 / image |
Kling V3 Image Kuaishou | Text to image, Image edit | — | 2 / image |
Hunyuan Image 3.5 Tencent | Text to image, Image edit | — | 2 / image |
Grok Imagine xAI | Text to image, Image edit | — | 2 / image |
FLUX.2 Dev Black Forest Labs | Text to image, Image edit | — | 3 / image |
FLUX.2 Klein 9B Black Forest Labs | Text to image, Image edit | — | 1 / image |
FLUX.2 Klein 4B Black Forest Labs | Text to image, Image edit | — | Free |
Z-Image Turbo Alibaba Tongyi · Open model | Text to image | — | Free |
Chroma Lodestone · Open model | Text to image | — | 1 / image |
WAI Illustrious Community · Open model | Text to image | — | Free |
Krea 2 Turbo Krea · Open model | Text to image | — | 1 / image |
HiDream I1 HiDream.ai · Open model | Text to image | — | 1 / image |
Stable Diffusion 3.5 Large Stability AI · Open model | Text to image | — | 1 / image |
SDXL Stability AI · Open model | Text to image | — | Free |
Pony Diffusion Community · Open model | Text to image | — | Free |
Phoenix 1.0 Leonardo.Ai | Text to image | — | 2 / image |
Lucid Origin Leonardo.Ai | Text to image | — | 2 / image |
Image edit
4 machinesFLUX Kontext Pro
Black Forest Labs · Image edit
Image edit
3 / imagePull
Qwen Image Edit
Alibaba · Image edit
Open modelImage edit
2 / imagePull
Seedream 5.0 Edit
ByteDance · Image edit
Image edit
3 / imagePull
Nano Banana Pro Edit
Google · Image edit
Image edit
4 / imagePull
| Model | How to make it | Length · Resolution | Credits / image |
|---|---|---|---|
FLUX Kontext Pro Black Forest Labs | Image edit | — | 3 / image |
Qwen Image Edit Alibaba · Open model | Image edit | — | 2 / image |
Seedream 5.0 Edit ByteDance | Image edit | — | 3 / image |
Nano Banana Pro Edit Google | Image edit | — | 4 / image |
Video
26 machinesSeedance 2.5
ByteDance · Video
New4–30s · 1080p · With sound
8 / secPull
Seedance 2.0
ByteDance · Video
4–15s · 4K · With sound
6 / secPull
Seedance 2.0 Mini
ByteDance · Video
Fast4–15s · 720p · With sound
3 / secPull
Wan 3.0
Alibaba · Video
New2–30s · 1080p · With sound
4 / secPull
Wan 3.0 Prime
Alibaba · Video
Pro2–30s · 1080p · With sound
6 / secPull
Wan 2.6
Alibaba · Video
5–15s · 1080p · With sound
3 / secPull
Wan 2.5
Alibaba · Video
5–10s · 1080p · With sound
3 / secPull
Wan 2.7
Alibaba · Video
2–15s · 1080p
3 / secPull
MiniMax H3
MiniMax · Video
New5–15s · 1440p
3 / secPull
MiniMax H3 Max
MiniMax · Video
Pro5–15s · 768p
5 / secPull
MiniMax H3 Turbo
MiniMax · Video
Fast5–15s · 768p
2 / secPull
Hailuo 2.3
MiniMax · Video
6–10s · 1080p
4 / secPull
Kling V3
Kuaishou · Video
3–15s · 4K · With sound
7 / secPull
Kling O3 Omni
Kuaishou · Video
Pro3–15s · 4K · With sound
8 / secPull
Kling 3.0 Turbo
Kuaishou · Video
Fast3–15s · 1080p
4 / secPull
Kling Motion Control
Kuaishou · Video
3–30s · 1080p
6 / secPull
Veo 3.1
Google · Video
Pro4–8s · 4K · With sound
12 / secPull
Veo 3.1 Fast
Google · Video
Fast4–8s · 1080p · With sound
6 / secPull
Gemini Omni Flash
Google · Video
New3–10s · 4K
6 / secPull
FLUX 3 Video
Black Forest Labs · Video
New5–20s · 1080p · With sound
6 / secPull
Happy Horse 1.1
Alibaba · Video
3–15s · 1080p
4 / secPull
Grok Imagine Video 1.5
xAI · Video
1–15s · 720p
3 / secPull
Vidu Q3 Pro
Shengshu · Video
1–16s · 1080p · With sound
5 / secPull
Wan 2.2 (open)
Alibaba · Video
Open model2–5s · 720p
2 / secPull
HunyuanVideo 1.5
Tencent · Video
2–10s · 720p
2 / secPull
LTX-2
Lightricks · Video
Open model2–10s · 1080p · With sound
2 / secPull
| Model | How to make it | Length · Resolution | Credits / image |
|---|---|---|---|
Seedance 2.5 ByteDance | Text to video, Image to video | 4–30s · 480p / 720p / 1080p · With sound | 8 / sec |
Seedance 2.0 ByteDance | Text to video, Image to video, Video edit | 4–15s · 480p / 720p / 1080p / 4K · With sound | 6 / sec |
Seedance 2.0 Mini ByteDance | Text to video, Image to video | 4–15s · 480p / 720p · With sound | 3 / sec |
Wan 3.0 Alibaba | Text to video, Image to video, Video edit | 2–30s · 480p / 720p / 1080p · With sound | 4 / sec |
Wan 3.0 Prime Alibaba | Text to video, Image to video | 2–30s · 480p / 720p / 1080p · With sound | 6 / sec |
Wan 2.6 Alibaba | Text to video, Image to video | 5–15s · 720p / 1080p · With sound | 3 / sec |
Wan 2.5 Alibaba | Text to video, Image to video | 5–10s · 480p / 720p / 1080p · With sound | 3 / sec |
Wan 2.7 Alibaba | Text to video, Image to video, Reference to video, Video edit | 2–15s · 720p / 1080p | 3 / sec |
MiniMax H3 MiniMax | Text to video, Image to video | 5–15s · 480p / 768p / 1440p | 3 / sec |
MiniMax H3 Max MiniMax | Text to video, Image to video | 5–15s · 480p / 768p | 5 / sec |
MiniMax H3 Turbo MiniMax | Text to video, Image to video | 5–15s · 480p / 768p | 2 / sec |
Hailuo 2.3 MiniMax | Text to video, Image to video | 6–10s · 768p / 1080p | 4 / sec |
Kling V3 Kuaishou | Text to video, Image to video | 3–15s · 720p / 1080p / 4K · With sound | 7 / sec |
Kling O3 Omni Kuaishou | Text to video, Image to video, Reference to video, Video edit | 3–15s · 720p / 1080p / 4K · With sound | 8 / sec |
Kling 3.0 Turbo Kuaishou | Text to video, Image to video | 3–15s · 720p / 1080p | 4 / sec |
Kling Motion Control Kuaishou | Video edit | 3–30s · 720p / 1080p | 6 / sec |
Veo 3.1 Google | Text to video, Image to video, Reference to video | 4–8s · 720p / 1080p / 4K · With sound | 12 / sec |
Veo 3.1 Fast Google | Text to video, Image to video | 4–8s · 720p / 1080p · With sound | 6 / sec |
Gemini Omni Flash Google | Text to video, Image to video, Reference to video, Video edit | 3–10s · 720p / 1080p / 4K | 6 / sec |
FLUX 3 Video Black Forest Labs | Text to video, Image to video | 5–20s · 720p / 1080p · With sound | 6 / sec |
Happy Horse 1.1 Alibaba | Text to video, Image to video, Reference to video | 3–15s · 720p / 1080p | 4 / sec |
Grok Imagine Video 1.5 xAI | Text to video, Image to video, Reference to video | 1–15s · 480p / 720p | 3 / sec |
Vidu Q3 Pro Shengshu | Text to video, Image to video | 1–16s · 540p / 720p / 1080p · With sound | 5 / sec |
Wan 2.2 (open) Alibaba · Open model | Text to video, Image to video | 2–5s · 480p / 720p | 2 / sec |
HunyuanVideo 1.5 Tencent | Text to video, Image to video | 2–10s · 480p / 720p | 2 / sec |
LTX-2 Lightricks · Open model | Text to video, Image to video | 2–10s · 720p / 1080p · With sound | 2 / sec |
Audio
19 machinesSeed Audio 1.0
ByteDance · Audio
New5–120s
6 / trackPull
Eleven v4
ElevenLabs · Audio
ProText to speech · Voice clone
6 / 1k charsPull
Eleven v3
ElevenLabs · Audio
Text to speech · Voice clone
5 / 1k charsPull
MiniMax Speech 2.8 HD
MiniMax · Audio
Text to speech · Voice clone
4 / 1k charsPull
Seed Speech TTS 2.0
ByteDance · Audio
Text to speech · Voice clone
3 / 1k charsPull
Gemini Flash TTS
Google · Audio
Text to speech
2 / 1k charsPull
Grok Voice TTS
xAI · Audio
Text to speech
2 / 1k charsPull
Chatterbox Multilingual
Resemble AI · Audio
Open modelText to speech · Voice clone
1 / 1k charsPull
Qwen3-TTS
Alibaba · Audio
Open modelText to speech · Voice clone
1 / 1k charsPull
CosyVoice 3
Alibaba · Audio
Open modelText to speech · Voice clone
1 / 1k charsPull
Kokoro 82M
hexgrad · Audio
Open modelText to speech
FreePull
Eleven Music v2.5
ElevenLabs · Audio
New10–300s
20 / trackPull
Lyria 3
Google DeepMind · Audio
10–180s
15 / trackPull
Stable Audio 3
Stability AI · Audio
5–190s
10 / trackPull
ACE-Step 1.5
ACE Studio · Audio
Open model10–240s
4 / trackPull
Eleven Sound Effects v2
ElevenLabs · Audio
1–30s
4 / trackPull
Mirelo SFX 1.6
Mirelo AI · Audio
1–30s
3 / trackPull
Kling Video-to-Audio
Kuaishou · Audio
1–20s
3 / trackPull
ThinkSound
Alibaba · Audio
Open model1–30s
1 / trackPull
| Model | How to make it | Length · Resolution | Credits / image |
|---|---|---|---|
Seed Audio 1.0 ByteDance | Text to speech, Music, Sound effects | 5–120s | 6 / track |
Eleven v4 ElevenLabs | Text to speech, Voice clone | — | 6 / 1k chars |
Eleven v3 ElevenLabs | Text to speech, Voice clone | — | 5 / 1k chars |
MiniMax Speech 2.8 HD MiniMax | Text to speech, Voice clone | — | 4 / 1k chars |
Seed Speech TTS 2.0 ByteDance | Text to speech, Voice clone | — | 3 / 1k chars |
Gemini Flash TTS Google | Text to speech | — | 2 / 1k chars |
Grok Voice TTS xAI | Text to speech | — | 2 / 1k chars |
Chatterbox Multilingual Resemble AI · Open model | Text to speech, Voice clone | — | 1 / 1k chars |
Qwen3-TTS Alibaba · Open model | Text to speech, Voice clone | — | 1 / 1k chars |
CosyVoice 3 Alibaba · Open model | Text to speech, Voice clone | — | 1 / 1k chars |
Kokoro 82M hexgrad · Open model | Text to speech | — | Free |
Eleven Music v2.5 ElevenLabs | Music | 10–300s | 20 / track |
Lyria 3 Google DeepMind | Music | 10–180s | 15 / track |
Stable Audio 3 Stability AI | Music, Sound effects | 5–190s | 10 / track |
ACE-Step 1.5 ACE Studio · Open model | Music | 10–240s | 4 / track |
Eleven Sound Effects v2 ElevenLabs | Sound effects | 1–30s | 4 / track |
Mirelo SFX 1.6 Mirelo AI | Sound effects | 1–30s | 3 / track |
Kling Video-to-Audio Kuaishou | Sound effects | 1–20s | 3 / track |
ThinkSound Alibaba · Open model | Sound effects | 1–30s | 1 / track |
Ratio
| 1:1 | Instagram · avatars |
| 3:4 | Xiaohongshu |
| 4:5 | Instagram feed |
| 9:16 | Reels · wallpaper |
| 4:3 | Blog |
| 16:9 | YouTube |
| 2:3 | Poster |
| 3:2 | Photo · print |