Files
2024-11-05 14:37:40 +00:00

1063 lines
51 KiB
JSON

{
"url": "https://replicate.com/stability-ai/sdxl",
"owner": "stability-ai",
"name": "sdxl",
"description": "A text-to-image generative AI model that creates beautiful images",
"visibility": "public",
"github_url": "https://github.com/replicate/cog-sdxl",
"paper_url": "https://arxiv.org/abs/2307.01952",
"license_url": "https://github.com/Stability-AI/generative-models/blob/main/model_licenses/LICENSE-SDXL1.0",
"run_count": 0,
"cover_image_url": "https://tjzk.replicate.delivery/models_models_featured_image/9065f9e3-40da-4742-8cb8-adfa8e794c0d/sdxl_cover.jpg",
"default_example": {
"id": "dzsqmb3bg4lqpjkz2iptjqgccm",
"model": "stability-ai/sdxl",
"version": "c221b2b8ef527988fb59bf24a8b97c4561f1c671f73bd389f866bfb27c061316",
"status": "succeeded",
"input": {
"width": 768,
"height": 768,
"prompt": "An astronaut riding a rainbow unicorn, cinematic, dramatic",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": false,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"num_inference_steps": 25
},
"output": [
"https://pbxt.replicate.delivery/YXbcLudoHBIYHV6L0HbcTx5iRzLFMwygLr3vhGpZI35caXbE/out-0.png"
],
"logs": "Using seed: 16010\nPrompt: An astronaut riding a rainbow unicorn, cinematic, dramatic\ntxt2img mode\n 0%| | 0/16 [00:00<?, ?it/s]\n 6%|▋ | 1/16 [00:00<00:01, 7.96it/s]\n 12%|█▎ | 2/16 [00:00<00:01, 7.89it/s]\n 19%|█▉ | 3/16 [00:00<00:01, 7.86it/s]\n 25%|██▌ | 4/16 [00:00<00:01, 7.85it/s]\n 31%|███▏ | 5/16 [00:00<00:01, 7.83it/s]\n 38%|███▊ | 6/16 [00:00<00:01, 7.82it/s]\n 44%|████▍ | 7/16 [00:00<00:01, 7.81it/s]\n 50%|█████ | 8/16 [00:01<00:01, 7.80it/s]\n 56%|█████▋ | 9/16 [00:01<00:00, 7.80it/s]\n 62%|██████▎ | 10/16 [00:01<00:00, 7.78it/s]\n 69%|██████▉ | 11/16 [00:01<00:00, 7.79it/s]\n 75%|███████▌ | 12/16 [00:01<00:00, 7.79it/s]\n 81%|████████▏ | 13/16 [00:01<00:00, 7.78it/s]\n 88%|████████▊ | 14/16 [00:01<00:00, 7.79it/s]\n 94%|█████████▍| 15/16 [00:01<00:00, 7.79it/s]\n100%|██████████| 16/16 [00:02<00:00, 7.79it/s]\n100%|██████████| 16/16 [00:02<00:00, 7.81it/s]\n 0%| | 0/5 [00:00<?, ?it/s]\n 20%|██ | 1/5 [00:00<00:00, 7.47it/s]\n 40%|████ | 2/5 [00:00<00:00, 7.42it/s]\n 60%|██████ | 3/5 [00:00<00:00, 7.40it/s]\n 80%|████████ | 4/5 [00:00<00:00, 7.39it/s]\n100%|██████████| 5/5 [00:00<00:00, 7.39it/s]\n100%|██████████| 5/5 [00:00<00:00, 7.40it/s]",
"error": null,
"metrics": {
"predict_time": 4.981337,
"total_time": 4.95241
},
"created_at": "2023-10-12T17:10:07.956869Z",
"started_at": "2023-10-12T17:10:07.927942Z",
"completed_at": "2023-10-12T17:10:12.909279Z",
"urls": {
"get": "https://api.replicate.com/v1/predictions/dzsqmb3bg4lqpjkz2iptjqgccm",
"cancel": "https://api.replicate.com/v1/predictions/dzsqmb3bg4lqpjkz2iptjqgccm/cancel"
}
},
"latest_version": {
"id": "7762fd07cf82c948538e41f63f77d685e02b063e37e496e96eefd46c929f9bdc",
"created_at": "2024-05-23T23:26:26.222931+00:00",
"cog_version": "0.9.5",
"openapi_schema": {
"info": {
"title": "Cog",
"version": "0.1.0"
},
"paths": {
"/": {
"get": {
"summary": "Root",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Root Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "root__get"
}
},
"/shutdown": {
"post": {
"summary": "Start Shutdown",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Start Shutdown Shutdown Post"
}
}
},
"description": "Successful Response"
}
},
"operationId": "start_shutdown_shutdown_post"
}
},
"/trainings": {
"post": {
"summary": "Train",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/TrainingResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"operationId": "train_trainings_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/TrainingRequest"
}
}
}
}
}
},
"/predictions": {
"post": {
"summary": "Predict",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model",
"operationId": "predict_predictions_post",
"requestBody": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionRequest"
}
}
}
}
}
},
"/health-check": {
"get": {
"summary": "Healthcheck",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Healthcheck Health Check Get"
}
}
},
"description": "Successful Response"
}
},
"operationId": "healthcheck_health_check_get"
}
},
"/trainings/{training_id}": {
"put": {
"summary": "Train Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "training_id",
"schema": {
"type": "string",
"title": "Training ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"operationId": "train_idempotent_trainings__training_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/TrainingRequest"
}
],
"title": "Training Request"
}
}
},
"required": true
}
}
},
"/predictions/{prediction_id}": {
"put": {
"summary": "Predict Idempotent",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/PredictionResponse"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
},
{
"in": "header",
"name": "prefer",
"schema": {
"type": "string",
"title": "Prefer"
},
"required": false
}
],
"description": "Run a single prediction on the model (idempotent creation).",
"operationId": "predict_idempotent_predictions__prediction_id__put",
"requestBody": {
"content": {
"application/json": {
"schema": {
"allOf": [
{
"$ref": "#/components/schemas/PredictionRequest"
}
],
"title": "Prediction Request"
}
}
},
"required": true
}
}
},
"/trainings/{training_id}/cancel": {
"post": {
"summary": "Cancel Training",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Training Trainings Training Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "training_id",
"schema": {
"type": "string",
"title": "Training ID"
},
"required": true
}
],
"operationId": "cancel_training_trainings__training_id__cancel_post"
}
},
"/predictions/{prediction_id}/cancel": {
"post": {
"summary": "Cancel",
"responses": {
"200": {
"content": {
"application/json": {
"schema": {
"title": "Response Cancel Predictions Prediction Id Cancel Post"
}
}
},
"description": "Successful Response"
},
"422": {
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/HTTPValidationError"
}
}
},
"description": "Validation Error"
}
},
"parameters": [
{
"in": "path",
"name": "prediction_id",
"schema": {
"type": "string",
"title": "Prediction ID"
},
"required": true
}
],
"description": "Cancel a running prediction",
"operationId": "cancel_predictions__prediction_id__cancel_post"
}
}
},
"openapi": "3.0.2",
"components": {
"schemas": {
"Input": {
"type": "object",
"title": "Input",
"properties": {
"mask": {
"type": "string",
"title": "Mask",
"format": "uri",
"x-order": 3,
"description": "Input mask for inpaint mode. Black areas will be preserved, white areas will be inpainted."
},
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 11,
"description": "Random seed. Leave blank to randomize the seed"
},
"image": {
"type": "string",
"title": "Image",
"format": "uri",
"x-order": 2,
"description": "Input image for img2img or inpaint mode"
},
"width": {
"type": "integer",
"title": "Width",
"default": 1024,
"x-order": 4,
"description": "Width of output image"
},
"height": {
"type": "integer",
"title": "Height",
"default": 1024,
"x-order": 5,
"description": "Height of output image"
},
"prompt": {
"type": "string",
"title": "Prompt",
"default": "An astronaut riding a rainbow unicorn",
"x-order": 0,
"description": "Input prompt"
},
"refine": {
"allOf": [
{
"$ref": "#/components/schemas/refine"
}
],
"default": "no_refiner",
"x-order": 12,
"description": "Which refine style to use"
},
"scheduler": {
"allOf": [
{
"$ref": "#/components/schemas/scheduler"
}
],
"default": "K_EULER",
"x-order": 7,
"description": "scheduler"
},
"lora_scale": {
"type": "number",
"title": "Lora Scale",
"default": 0.6,
"maximum": 1,
"minimum": 0,
"x-order": 16,
"description": "LoRA additive scale. Only applicable on trained models."
},
"num_outputs": {
"type": "integer",
"title": "Num Outputs",
"default": 1,
"maximum": 4,
"minimum": 1,
"x-order": 6,
"description": "Number of images to output."
},
"refine_steps": {
"type": "integer",
"title": "Refine Steps",
"x-order": 14,
"description": "For base_image_refiner, the number of steps to refine, defaults to num_inference_steps"
},
"guidance_scale": {
"type": "number",
"title": "Guidance Scale",
"default": 7.5,
"maximum": 50,
"minimum": 1,
"x-order": 9,
"description": "Scale for classifier-free guidance"
},
"apply_watermark": {
"type": "boolean",
"title": "Apply Watermark",
"default": true,
"x-order": 15,
"description": "Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking."
},
"high_noise_frac": {
"type": "number",
"title": "High Noise Frac",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 13,
"description": "For expert_ensemble_refiner, the fraction of noise to use"
},
"negative_prompt": {
"type": "string",
"title": "Negative Prompt",
"default": "",
"x-order": 1,
"description": "Input Negative Prompt"
},
"prompt_strength": {
"type": "number",
"title": "Prompt Strength",
"default": 0.8,
"maximum": 1,
"minimum": 0,
"x-order": 10,
"description": "Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image"
},
"replicate_weights": {
"type": "string",
"title": "Replicate Weights",
"x-order": 17,
"description": "Replicate LoRA weights to use. Leave blank to use the default weights."
},
"num_inference_steps": {
"type": "integer",
"title": "Num Inference Steps",
"default": 50,
"maximum": 500,
"minimum": 1,
"x-order": 8,
"description": "Number of denoising steps"
},
"disable_safety_checker": {
"type": "boolean",
"title": "Disable Safety Checker",
"default": false,
"x-order": 18,
"description": "Disable safety checker for generated images. This feature is only available through the API. See [https://replicate.com/docs/how-does-replicate-work#safety](https://replicate.com/docs/how-does-replicate-work#safety)"
}
}
},
"Output": {
"type": "array",
"items": {
"type": "string",
"format": "uri"
},
"title": "Output"
},
"Status": {
"enum": [
"starting",
"processing",
"succeeded",
"canceled",
"failed"
],
"type": "string",
"title": "Status",
"description": "An enumeration."
},
"refine": {
"enum": [
"no_refiner",
"expert_ensemble_refiner",
"base_image_refiner"
],
"type": "string",
"title": "refine",
"description": "An enumeration."
},
"scheduler": {
"enum": [
"DDIM",
"DPMSolverMultistep",
"HeunDiscrete",
"KarrasDPM",
"K_EULER_ANCESTRAL",
"K_EULER",
"PNDM"
],
"type": "string",
"title": "scheduler",
"description": "An enumeration."
},
"WebhookEvent": {
"enum": [
"start",
"output",
"logs",
"completed"
],
"type": "string",
"title": "WebhookEvent",
"description": "An enumeration."
},
"lr_scheduler": {
"enum": [
"constant",
"linear"
],
"type": "string",
"title": "lr_scheduler",
"description": "An enumeration."
},
"TrainingInput": {
"type": "object",
"title": "TrainingInput",
"required": [
"input_images"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 1,
"description": "Random seed for reproducible training. Leave empty to use a random seed"
},
"ti_lr": {
"type": "number",
"title": "Ti Lr",
"default": 0.0003,
"x-order": 8,
"description": "Scaling of learning rate for training textual inversion embeddings. Don't alter unless you know what you're doing."
},
"is_lora": {
"type": "boolean",
"title": "Is Lora",
"default": true,
"x-order": 6,
"description": "Whether to use LoRA training. If set to False, will use Full fine tuning"
},
"lora_lr": {
"type": "number",
"title": "Lora Lr",
"default": 0.0001,
"x-order": 9,
"description": "Scaling of learning rate for training LoRA embeddings. Don't alter unless you know what you're doing."
},
"verbose": {
"type": "boolean",
"title": "Verbose",
"default": true,
"x-order": 19,
"description": "verbose output"
},
"lora_rank": {
"type": "integer",
"title": "Lora Rank",
"default": 32,
"x-order": 10,
"description": "Rank of LoRA embeddings. Don't alter unless you know what you're doing."
},
"resolution": {
"type": "integer",
"title": "Resolution",
"default": 768,
"x-order": 2,
"description": "Square pixel resolution which your images will be resized to for training"
},
"input_images": {
"type": "string",
"title": "Input Images",
"format": "uri",
"x-order": 0,
"description": "A .zip or .tar file containing the image files that will be used for fine-tuning"
},
"lr_scheduler": {
"allOf": [
{
"$ref": "#/components/schemas/lr_scheduler"
}
],
"default": "constant",
"x-order": 11,
"description": "Learning rate scheduler to use for training"
},
"token_string": {
"type": "string",
"title": "Token String",
"default": "TOK",
"x-order": 13,
"description": "A unique string that will be trained to refer to the concept in the input images. Can be anything, but TOK works well"
},
"caption_prefix": {
"type": "string",
"title": "Caption Prefix",
"default": "a photo of TOK, ",
"x-order": 14,
"description": "Text which will be used as prefix during automatic captioning. Must contain the `token_string`. For example, if caption text is 'a photo of TOK', automatic captioning will expand to 'a photo of TOK under a bridge', 'a photo of TOK holding a cup', etc."
},
"lr_warmup_steps": {
"type": "integer",
"title": "Lr Warmup Steps",
"default": 100,
"x-order": 12,
"description": "Number of warmup steps for lr schedulers with warmups."
},
"max_train_steps": {
"type": "integer",
"title": "Max Train Steps",
"default": 1000,
"x-order": 5,
"description": "Number of individual training steps. Takes precedence over num_train_epochs"
},
"num_train_epochs": {
"type": "integer",
"title": "Num Train Epochs",
"default": 4000,
"x-order": 4,
"description": "Number of epochs to loop through your training dataset"
},
"train_batch_size": {
"type": "integer",
"title": "Train Batch Size",
"default": 4,
"x-order": 3,
"description": "Batch size (per device) for training"
},
"unet_learning_rate": {
"type": "number",
"title": "Unet Learning Rate",
"default": 1e-06,
"x-order": 7,
"description": "Learning rate for the U-Net. We recommend this value to be somewhere between `1e-6` to `1e-5`."
},
"checkpointing_steps": {
"type": "integer",
"title": "Checkpointing Steps",
"default": 999999,
"x-order": 20,
"description": "Number of steps between saving checkpoints. Set to very very high number to disable checkpointing, because you don't need one."
},
"clipseg_temperature": {
"type": "number",
"title": "Clipseg Temperature",
"default": 1,
"x-order": 18,
"description": "How blurry you want the CLIPSeg mask to be. We recommend this value be something between `0.5` to `1.0`. If you want to have more sharp mask (but thus more errorful), you can decrease this value."
},
"mask_target_prompts": {
"type": "string",
"title": "Mask Target Prompts",
"x-order": 15,
"description": "Prompt that describes part of the image that you will find important. For example, if you are fine-tuning your pet, `photo of a dog` will be a good prompt. Prompt-based masking is used to focus the fine-tuning process on the important/salient parts of the image"
},
"input_images_filetype": {
"allOf": [
{
"$ref": "#/components/schemas/input_images_filetype"
}
],
"default": "infer",
"x-order": 21,
"description": "Filetype of the input images. Can be either `zip` or `tar`. By default its `infer`, and it will be inferred from the ext of input file."
},
"crop_based_on_salience": {
"type": "boolean",
"title": "Crop Based On Salience",
"default": true,
"x-order": 16,
"description": "If you want to crop the image to `target_size` based on the important parts of the image, set this to True. If you want to crop the image based on face detection, set this to False"
},
"use_face_detection_instead": {
"type": "boolean",
"title": "Use Face Detection Instead",
"default": false,
"x-order": 17,
"description": "If you want to use face detection instead of CLIPSeg for masking. For face applications, we recommend using this option."
}
}
},
"TrainingOutput": {
"type": "object",
"title": "TrainingOutput",
"required": [
"weights"
],
"properties": {
"weights": {
"type": "string",
"title": "Weights",
"format": "uri"
}
}
},
"TrainingRequest": {
"type": "object",
"title": "TrainingRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/TrainingInput"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"ValidationError": {
"type": "object",
"title": "ValidationError",
"required": [
"loc",
"msg",
"type"
],
"properties": {
"loc": {
"type": "array",
"items": {
"anyOf": [
{
"type": "string"
},
{
"type": "integer"
}
]
},
"title": "Location"
},
"msg": {
"type": "string",
"title": "Message"
},
"type": {
"type": "string",
"title": "Error Type"
}
}
},
"TrainingResponse": {
"type": "object",
"title": "TrainingResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/TrainingInput"
},
"output": {
"$ref": "#/components/schemas/TrainingOutput"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"PredictionRequest": {
"type": "object",
"title": "PredictionRequest",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"webhook": {
"type": "string",
"title": "Webhook",
"format": "uri",
"maxLength": 65536,
"minLength": 1
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"output_file_prefix": {
"type": "string",
"title": "Output File Prefix"
},
"webhook_events_filter": {
"type": "array",
"items": {
"$ref": "#/components/schemas/WebhookEvent"
},
"default": [
"start",
"output",
"logs",
"completed"
]
}
}
},
"PredictionResponse": {
"type": "object",
"title": "PredictionResponse",
"properties": {
"id": {
"type": "string",
"title": "Id"
},
"logs": {
"type": "string",
"title": "Logs",
"default": ""
},
"error": {
"type": "string",
"title": "Error"
},
"input": {
"$ref": "#/components/schemas/Input"
},
"output": {
"$ref": "#/components/schemas/Output"
},
"status": {
"$ref": "#/components/schemas/Status"
},
"metrics": {
"type": "object",
"title": "Metrics"
},
"version": {
"type": "string",
"title": "Version"
},
"created_at": {
"type": "string",
"title": "Created At",
"format": "date-time"
},
"started_at": {
"type": "string",
"title": "Started At",
"format": "date-time"
},
"completed_at": {
"type": "string",
"title": "Completed At",
"format": "date-time"
}
}
},
"HTTPValidationError": {
"type": "object",
"title": "HTTPValidationError",
"properties": {
"detail": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ValidationError"
},
"title": "Detail"
}
}
},
"input_images_filetype": {
"enum": [
"zip",
"tar",
"infer"
],
"type": "string",
"title": "input_images_filetype",
"description": "An enumeration."
}
}
}
}
}
}