replicate-python
replicate-python copied to clipboard
replicate
Python client for Replicate
How can I execute a prompt, where I tell the model give me back in a specific JSON format? I know that the { are used for instructions prompt_template={prompt} But...
This PR adds markdown API reference in the `docs` folder and updates the Release workflow to automatically generate and commit the docs. I am not a Github Actions adept so...
Is there any ability to batch process similar to how OpenAI do it: https://help.openai.com/en/articles/9197833-batch-api-faq?
Hi everyone! I am using the replicate API to generate some images with focus-api model with the replicate.run() method in python. As I am generating more images at once, the...
Hi I am running this code: training = replicate.trainings.create( destination="kartikwar/business-card", model="stability-ai/sdxl", version="39ed52f2a78e934b3ba6e2a89f5b1c712de7dfea535525255b1aa35c5565e08b", input={ "input_images": "https://uploads.documents.cimpress.io/v1/uploads/94bc6c51-8cfc-4bbd-96fe-389facc3c0c5~122?tenant=furl", "token_string": "business card", "caption_prefix": "an image of business card", "max_train_steps": 1000, "use_face_detection_instead": False, "crop_based_on_salience": False...
I believe that if a user has configured a proxy, it should be ensured that the proxy is applied. It took me 5 hours to find the reason for the...
- update first example to point to Llama 3 - make it more explicit you can always check out a models API page (with link) - provide an async example...
I'm fine tunning Llama-2 13-b model with jsonl file it fails. I've tried with 7b model and I've enabled billing also. ```python DESTINATION_MODEL_NAME = 'deepakkumar07-debug/llama-midjournery' TRAINING_DATA_URL = 'https://sangli-training-dataset.s3.ap-south-1.amazonaws.com/midjourney_replicate_dataset.jsonl' training =...
Add the missing verb 'list' to the sentence 'You can the models you've created' under the 'List models' section.
