NodeTool Cloud is in alpha — run workflows in the browser, on your own keys.NodeTool Cloud is in alpha. Try it →
Model provider · Bring your own keyAtlasCloud in a visual AI workflow
Run AtlasCloud's chat, image and video models in a visual AI workflow — DeepSeek, Seedance, GPT-Image and more, called with your own key at AtlasCloud's price.
AtlasCloud serves chat, image and video models through a single API. NodeTool exposes each image and video model as a node, and AtlasCloud's text models appear in the regular model picker alongside every other chat provider.
Wire an AtlasCloud image model into a video model, add an upscaler, and you have a repeatable pipeline you can re-run and share. Swapping AtlasCloud for another provider is a single node change.
AtlasCloud runs on your own key: NodeTool calls it with your `ATLASCLOUD_API_KEY` at their list price. The catalog below comes from AtlasCloud's node manifest.
Requests go straight to AtlasCloud with your key at their list price. NodeTool never sits in the middle and never adds a markup.
What you can build with AtlasCloud
Supported AtlasCloud models
Each model below is its own node in NodeTool — the id is what AtlasCloud serves it under. This list is generated from AtlasCloud's node manifest, so it tracks what the provider actually ships.
Image models
76 totalalibaba/wan-2.6/image-editAtlasCloud / Alibaba Wan 2.6 — edits input images from a text instruction.
alibaba/wan-2.6/text-to-imageAtlasCloud / Alibaba Wan 2.6 — text to image with a negative prompt and a wide size list.
alibaba/wan-2.7-pro/image-editAtlasCloud / Alibaba Wan 2.7 Pro — higher-quality image editing from text instructions with multi-image references.
alibaba/wan-2.7-pro/text-to-imageAtlasCloud / Alibaba Wan 2.7 Pro — higher-fidelity text-to-image with 4K-ready output.
alibaba/wan-2.7/image-editAtlasCloud / Alibaba Wan 2.7 — edits and recomposes images from text instructions with multi-image references.
alibaba/wan-2.7/text-to-imageAtlasCloud / Alibaba Wan 2.7 — fast text-to-image with strong prompt fidelity for illustration and photorealistic outputs.
atlascloud/image-upscalerAtlasCloud Image Upscaler — enlarges an image up to 4x without a prompt.
atlascloud/photo-cleanupAtlasCloud Photo Cleanup — removes compression artifacts and noise from a photo.
black-forest-labs/flux-2-flex/editAtlasCloud / Black Forest Labs FLUX.2 Flex — image editing with exposed guidance and step count.
black-forest-labs/flux-2-flex/text-to-imageAtlasCloud / Black Forest Labs FLUX.2 Flex — text to image with exposed guidance and step count.
black-forest-labs/flux-2-pro/editAtlasCloud / Black Forest Labs FLUX.2 Pro — edits up to 8 input images from a text instruction.
black-forest-labs/flux-2-pro/text-to-imageAtlasCloud / Black Forest Labs FLUX.2 Pro — text to image with high prompt adherence and legible text.
black-forest-labs/flux-devAtlasCloud / Black Forest Labs FLUX.1 Dev — text to image, or image to image when a source image is connected.
black-forest-labs/flux-kontext-devAtlasCloud / Black Forest Labs FLUX.1 Kontext Dev — instruction-driven image editing that keeps the rest of the frame.
black-forest-labs/flux-schnellAtlasCloud / Black Forest Labs FLUX.1 Schnell — the fast distilled FLUX.
bytedance/seedream-v4.5AtlasCloud / ByteDance Seedream v4.5 — text to image up to 4K.
bytedance/seedream-v4.5/editAtlasCloud / ByteDance Seedream v4.5 — edits input images from a text instruction.
bytedance/seedream-v5.0-liteAtlasCloud / ByteDance Seedream v5.0 Lite — next-generation text-to-image with enhanced typography and poster design.
bytedance/seedream-v5.0-lite/editAtlasCloud / ByteDance Seedream v5.0 Lite — image editing that preserves facial features, lighting, and color tones.
bytedance/seedream-v5.0-pro/editAtlasCloud / ByteDance Seedream v5.0 Pro — professional image editing with up to 10 reference images, preserving identity, lighting, and color tones.
bytedance/seedream-v5.0-pro/text-to-imageAtlasCloud / ByteDance Seedream v5.0 Pro — flagship next-generation text-to-image with stronger prompt adherence.
google/nano-banana-2-lite/editAtlasCloud / Google Nano Banana 2 Lite — fast multi-turn local edits (up to 14 input images).
google/nano-banana-2-lite/text-to-imageAtlasCloud / Google Nano Banana 2 Lite — fast, cost-efficient 1K text-to-image with sub-2-second latency.
google/nano-banana-2/editAtlasCloud / Google Nano Banana 2 — guided-diffusion image editing (up to 14 input images).
google/nano-banana-2/text-to-imageAtlasCloud / Google Nano Banana 2 — fast 4K-capable text-to-image with native text rendering.
google/nano-banana-pro/editAtlasCloud / Google Nano Banana Pro — higher-quality image editing with optional web grounding.
google/nano-banana-pro/edit-ultraAtlasCloud / Google Nano Banana Pro Ultra — 4K/8K image editing.
google/nano-banana-pro/text-to-imageAtlasCloud / Google Nano Banana Pro — higher-quality T2I with optional web grounding.
google/nano-banana-pro/text-to-image-ultraAtlasCloud / Google Nano Banana Pro Ultra — 4K/8K text-to-image.
hidream-o1-1.5/editAtlasCloud / HiDream O1 1.5 — edits reference images from a text instruction.
hidream-o1-1.5/text-to-imageAtlasCloud / HiDream O1 1.5 — text to image with optional reference images for style or subject.
ideogram/v4/quality/text-to-imageAtlasCloud / Ideogram v4 Quality — the slower, higher-fidelity Ideogram v4 tier.
ideogram/v4/turbo/text-to-imageAtlasCloud / Ideogram v4 Turbo — fast text to image, strong at typography and logos.
krea-2-turbo/text-to-imageAtlasCloud / Krea 2 Turbo — fast text to image tuned against the over-processed look.
microsoft/mai-image-2.5-flash/editAtlasCloud / Microsoft MAI-Image-2.5-Flash — fast single-image editing from a text instruction.
microsoft/mai-image-2.5-flash/text-to-imageAtlasCloud / Microsoft MAI Image 2.5 Flash — fast, cost-optimized text-to-image.
microsoft/mai-image-2.5/editAtlasCloud / Microsoft MAI Image 2.5 — natural-language-guided image editing.
microsoft/mai-image-2.5/text-to-imageAtlasCloud / Microsoft MAI Image 2.5 — flagship high-quality text-to-image.
nvidia/cosmos-3-super/text-to-imageAtlasCloud / NVIDIA Cosmos 3 Super — text to image with a negative prompt and exposed sampler settings.
openai/gpt-image-1-mini/editAtlasCloud / OpenAI GPT Image 1 Mini — the cheaper edit tier for drafts and volume.
+ 36 more image models available in AtlasCloud.
Video models
81 totalalibaba/happyhorse-1.1/image-to-videoAtlasCloud / Alibaba HappyHorse 1.1 — animates a first-frame image into a 3-15 second video.
alibaba/happyhorse-1.1/reference-to-videoAtlasCloud / Alibaba HappyHorse 1.1 — generates video from 1-9 reference images with a text prompt.
alibaba/happyhorse-1.1/text-to-videoAtlasCloud / Alibaba HappyHorse 1.1 — 720P/1080P text-to-video, 3-15 second durations.
alibaba/wan-2.6/image-to-videoAtlasCloud / Alibaba Wan 2.6 — animates a still image, optionally driven by an audio track.
alibaba/wan-2.6/text-to-videoAtlasCloud / Alibaba Wan 2.6 — 5, 10 or 15 second text to video, optionally driven by an audio track.
alibaba/wan-2.7/image-to-videoAtlasCloud / Alibaba Wan 2.7 — animates images into video with first-frame, first-and-last-frame, video continuation, and audio-driven modes.
alibaba/wan-2.7/reference-to-videoAtlasCloud / Alibaba Wan 2.7 — generates video from reference images, videos and an optional audio track.
alibaba/wan-2.7/text-to-videoAtlasCloud / Alibaba Wan 2.7 — generates video from text with multi-shot narrative, audio generation, and sound-image synchronization.
alibaba/wan-2.7/video-editAtlasCloud / Alibaba Wan 2.7 — edits an existing video from a text instruction, with optional reference images.
alibaba/wan-3.0-prime/image-to-videoAtlasCloud / Alibaba Wan 3.0 Prime — animates a first frame (and an optional last frame) into hyper-real video.
alibaba/wan-3.0-prime/reference-to-videoAtlasCloud / Alibaba Wan 3.0 Prime — generates video from reference images, videos and audio.
alibaba/wan-3.0-prime/text-to-videoAtlasCloud / Alibaba Wan 3.0 Prime — hyper-real video from a text prompt, up to 30s with native audio.
alibaba/wan-3.0/image-to-videoAtlasCloud / Alibaba Wan 3.0 — animates a first frame (and an optional last frame) into cinematic video.
alibaba/wan-3.0/reference-to-videoAtlasCloud / Alibaba Wan 3.0 — generates video from reference images, videos and audio.
alibaba/wan-3.0/text-to-videoAtlasCloud / Alibaba Wan 3.0 — cinematic video from a text prompt, up to 30s with native audio.
atlascloud/video-upscalerAtlasCloud Video Upscaler — re-renders a clip at 1080p or 2K without a prompt.
bytedance/avatar-omni-human-v1.5AtlasCloud / ByteDance Omni Human 1.5 — digital-human video from a portrait image and driving audio, with lip-sync and natural gestures.
bytedance/seedance-2.0-fast/image-to-videoAtlasCloud / ByteDance Seedance 2.0 Fast — accelerated I2V from a first-frame image with native audio.
bytedance/seedance-2.0-fast/reference-to-videoAtlasCloud / ByteDance Seedance 2.0 Fast multimodal — accelerated multimodal video gen from reference images/videos/audio.
bytedance/seedance-2.0-fast/text-to-videoAtlasCloud / ByteDance Seedance 2.0 Fast — accelerated T2V with native audio.
bytedance/seedance-2.0-mini/image-to-videoAtlasCloud / ByteDance Seedance 2.0 Mini — lightweight first/last-frame animation with native audio.
bytedance/seedance-2.0-mini/reference-to-videoAtlasCloud / ByteDance Seedance 2.0 Mini multimodal — generates video from reference images, videos, and/or audio.
bytedance/seedance-2.0-mini/text-to-videoAtlasCloud / ByteDance Seedance 2.0 Mini — lightweight text-to-video with native audio.
bytedance/seedance-2.0/image-to-videoAtlasCloud / ByteDance Seedance 2.0 — generates video from a first-frame image (and optional last frame) with native audio.
bytedance/seedance-2.0/reference-to-videoAtlasCloud / ByteDance Seedance 2.0 multimodal — generates video from reference images, videos, and/or audio.
bytedance/seedance-2.0/text-to-videoAtlasCloud / ByteDance Seedance 2.0 — generates video from text with native audio.
bytedance/seedance-2.5/image-to-videoAtlasCloud / ByteDance Seedance 2.5 — animates a first frame (and an optional last frame) into video with native audio.
bytedance/seedance-2.5/reference-to-videoAtlasCloud / ByteDance Seedance 2.5 — generates video from reference images, videos and audio.
bytedance/seedance-2.5/text-to-videoAtlasCloud / ByteDance Seedance 2.5 — generates video from text with native audio, up to 30s and 4K.
bytedance/seedance-v1.5-pro/image-to-videoAtlasCloud / ByteDance Seedance v1.5 Pro — animates a first frame (and optional last frame) with native audio.
bytedance/seedance-v1.5-pro/text-to-videoAtlasCloud / ByteDance Seedance v1.5 Pro — text to video with native audio.
google/gemini-omni-flash/image-to-videoAtlasCloud / Google Gemini Omni Flash — cinematic animation from an input image, preserving subjects.
google/gemini-omni-flash/reference-to-videoAtlasCloud / Google Gemini Omni Flash — video generation from 1-5 reference images, maintaining subject consistency.
google/gemini-omni-flash/text-to-videoAtlasCloud / Google Gemini Omni Flash — cinematic text-to-video with synchronized native audio.
google/gemini-omni-flash/video-editAtlasCloud / Google Gemini Omni Flash — edits an existing video from a text prompt with optional reference images.
google/veo3.1-fast/image-to-videoAtlasCloud / Google Veo 3.1 Fast — speed-optimized image-to-video for fast previews and iteration.
google/veo3.1-fast/text-to-videoAtlasCloud / Google Veo 3.1 Fast — speed-optimized text-to-video for rapid creative iteration.
google/veo3.1-lite/image-to-videoAtlasCloud / Google Veo 3.1 Lite — cost-efficient image-to-video with synchronized audio at 720p/1080p.
google/veo3.1-lite/start-end-frame-to-videoAtlasCloud / Google Veo 3.1 Lite — interpolates between a first and a last frame.
google/veo3.1-lite/text-to-videoAtlasCloud / Google Veo 3.1 Lite — cost-efficient text-to-video with synchronized audio at 720p/1080p.
+ 41 more video models available in AtlasCloud.
Frequently asked questions
- How do I use AtlasCloud in NodeTool?
- Store your key as `ATLASCLOUD_API_KEY` in NodeTool settings. AtlasCloud nodes then call the API directly, and its chat models show up in the model picker.
- Which AtlasCloud models are supported?
- Every chat model AtlasCloud lists on its OpenAI-compatible endpoint, plus the image and video models in AtlasCloud's node manifest. See the catalog below.
- Does NodeTool add a markup?
- No. You pay AtlasCloud's list price with your own key.
Other providers
fal.ai
Replicate
Kie
Together AI
Topaz
Anthropic
OpenAI
Google Gemini
xAI Grok
Mistral AI
Groq
DeepSeek
Cohere
OpenRouter
Hugging Face
Meta AI
Cerebras
Alibaba Cloud
Moonshot (Kimi)
ElevenLabs
Reve
Meshy
Rodin (Hyper3D)
MiniMaxRun AtlasCloud your way.
Download NodeTool Studio and build across image, video, audio, and text with your own keys.