Move from V7 Darwin to Pictograph in two steps.
Bring your datasets over with the built-in V7 (Darwin) connector - images, annotations, and your folder structure come across, and V7's darwin_json_2 export converts to Pictograph JSON automatically. Start free, no credit card.
Import with the V7 connector
Two steps from the SDK, CLI, or app. Your Darwin key is used only to fetch your data.
from pictograph import Client
client = Client() # reads PICTOGRAPH_API_KEY
# 1. Validate your V7 (Darwin) API key and list its datasets.
result = client.connectors.validate(
provider="v7",
api_key="your_v7_darwin_api_key",
)
for ds in result.datasets:
print(ds.id, ds.name, ds.image_count)
# 2. Import the ones you want. Images, annotations, and folder
# structure come across, with V7's darwin_json_2 export converted
# to Pictograph JSON automatically. Large exports can take a while.
job = client.connectors.import_(
provider="v7",
api_key="your_v7_darwin_api_key",
datasets=result.datasets,
wait=True,
)
print(job.import_id, job.status)Prefer the app? Go to Datasets, then Import, then V7, paste your Darwin API key, and pick the datasets to bring over. Either way the import runs as a tracked job, and imported images get embeddings, content tags, and thumbnails just like a fresh upload, so they are searchable immediately. V7 nests images in folders, and the connector keeps that hierarchy - each item lands in the same directory path it had in Darwin. Large V7 exports can take 30 minutes or more, so the job streams progress the whole way through.
What comes across
Your images and their annotations - boxes, polygons, polylines, and keypoints - with class names preserved, image-level tags carried over as tag classes, and your folder structure intact. From there you can re-annotate with SAM3, add classes, or export in any of seven formats.
What you redo
Trained model weights, as with any platform switch. That is usually a feature, not a chore: retrain on Pictograph in one call and choose YOLOX for speed or RF-DETR for accuracy on hard scenes - and compare the two on your own data.
Label, train, and deploy from code
Once your data is in, the rest of the loop is one API - no sales call and no per-seat contract to negotiate first. Auto-annotate with SAM3 point, box, or text prompts - label "every forklift" across a directory in a single batch job - then train a detector or segmenter on a managed GPU and serve it as one authenticated /predict endpoint. The same REST API backs a typed Python SDK, a CLI, and a 37-tool agent registry, pricing is plain USD from $0, and your data stays private on every tier. See the connectors reference for the full import API and the YOLOX vs RF-DETR guide to pick a detector.
Migrating from V7 FAQ
Can I import my V7 datasets into Pictograph?
Yes. Pictograph has a built-in V7 (Darwin) connector. Validate your Darwin API key to list your datasets, then import the ones you want; the images and annotations are pulled directly, so there is no manual export-and-re-upload step. You can also import from the app: Datasets, then Import, then V7.
Will my annotations come across?
Yes. V7 datasets export as darwin_json_2, and Pictograph converts that to its canonical annotation format automatically - bounding boxes, polygons, polylines, and keypoints, with your class names preserved. Polygons pass through directly because both tools store paths, V7 lines become Pictograph polylines, and V7 image-level tags become tag classes. Any class missing a color is assigned a distinct one on import.
Does my folder structure survive the migration?
Yes. The V7 connector preserves each item’s folder path, so a nested Darwin dataset keeps its directory hierarchy in Pictograph instead of being flattened into one bucket. That is a real difference from a hand export and re-upload, where the folder tree is usually the first thing lost.
What happens to my trained V7 models?
Trained model weights do not transfer between platforms - that is true of any switch, not specific to Pictograph. Once your data is imported you retrain on Pictograph, often in one call: pick YOLOX for speed or RF-DETR for accuracy and train from the imported export. Auto-annotation with SAM3 can also fill in labels you never finished in V7.
Is there a free way to try the migration?
Yes. Pictograph’s free tier is $0 with no credit card and includes monthly compute, while V7 Darwin is priced for larger programs (a Basic free plan, then a Starter tier listed around $900/month in 2026). Import a V7 dataset, re-annotate with SAM3 or train a model, and evaluate the result before committing. Manual annotation is always free.