|
17 | 17 | - [Quickstart](#quickstart)
|
18 | 18 | - [Features](#features)
|
19 | 19 | - [Config](#config)
|
20 |
| - - [Upload image to AWS S3](#upload-image-to-aws-s3) |
| 20 | + * [Upload image to AWS S3](#upload-image-to-aws-s3) |
21 | 21 | - [Use the Docker image on RunPod](#use-the-docker-image-on-runpod)
|
22 |
| - - [Create your template (optional)](#create-your-template-optional) |
23 |
| - - [Create your endpoint](#create-your-endpoint) |
24 |
| - - [GPU recommendations](#gpu-recommendations) |
| 22 | + * [Create your template (optional)](#create-your-template-optional) |
| 23 | + * [Create your endpoint](#create-your-endpoint) |
| 24 | + * [GPU recommendations](#gpu-recommendations) |
25 | 25 | - [API specification](#api-specification)
|
26 |
| - - [JSON Request Body](#json-request-body) |
27 |
| - - [Fields](#fields) |
28 |
| - - ["input.images"](#inputimages) |
| 26 | + * [JSON Request Body](#json-request-body) |
| 27 | + * [Fields](#fields) |
| 28 | + + ["input.images"](#inputimages) |
29 | 29 | - [Interact with your RunPod API](#interact-with-your-runpod-api)
|
30 |
| - - [Health status](#health-status) |
31 |
| - - [Generate an image](#generate-an-image) |
32 |
| - - [Example request for SDXL with cURL](#example-request-for-sdxl-with-curl) |
| 30 | + * [Health status](#health-status) |
| 31 | + * [Generate an image](#generate-an-image) |
| 32 | + + [Example request for SDXL with cURL](#example-request-for-sdxl-with-curl) |
33 | 33 | - [How to get the workflow from ComfyUI?](#how-to-get-the-workflow-from-comfyui)
|
34 | 34 | - [Bring Your Own Models and Nodes](#bring-your-own-models-and-nodes)
|
35 |
| - - [Network Volume](#network-volume) |
36 |
| - - [Custom Docker Image](#custom-docker-image) |
37 |
| - - [Adding Custom Models](#adding-custom-models) |
38 |
| - - [Adding Custom Nodes](#adding-custom-nodes) |
39 |
| - - [Building the Image](#building-the-image) |
| 35 | + * [Network Volume](#network-volume) |
| 36 | + * [Custom Docker Image](#custom-docker-image) |
| 37 | + + [Adding Custom Models](#adding-custom-models) |
| 38 | + + [Adding Custom Nodes](#adding-custom-nodes) |
| 39 | + + [Building the Image](#building-the-image) |
40 | 40 | - [Local testing](#local-testing)
|
41 |
| - - [Setup](#setup) |
42 |
| - - [Setup for Windows](#setup-for-windows) |
43 |
| - - [Testing the RunPod handler](#testing-the-runpod-handler) |
44 |
| - - [Local API](#local-api) |
45 |
| - - [Access the local Worker API](#access-the-local-worker-api) |
46 |
| - - [Access local ComfyUI](#access-local-comfyui) |
| 41 | + * [Setup](#setup) |
| 42 | + + [Setup for Windows](#setup-for-windows) |
| 43 | + * [Testing the RunPod handler](#testing-the-runpod-handler) |
| 44 | + * [Local API](#local-api) |
| 45 | + + [Access the local Worker API](#access-the-local-worker-api) |
| 46 | + + [Access local ComfyUI](#access-local-comfyui) |
47 | 47 | - [Automatically deploy to Docker hub with GitHub Actions](#automatically-deploy-to-docker-hub-with-github-actions)
|
48 | 48 | - [Acknowledgments](#acknowledgments)
|
49 | 49 |
|
|
54 | 54 | ## Quickstart
|
55 | 55 |
|
56 | 56 | - 🐳 Choose one of the five available images for your serverless endpoint:
|
57 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-base`: doesn't contain anything, just a clean ComfyUI |
58 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-flux1-schnell`: contains the checkpoint, text encoders and VAE for [FLUX.1 schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) |
59 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-flux1-dev`: contains the checkpoint, text encoders and VAE for [FLUX.1 dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
60 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-sdxl`: contains the checkpoint and VAE for [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) |
61 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-sd3`: contains the checkpoint for [Stable Diffusion 3 medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium) |
| 57 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-base`: doesn't contain anything, just a clean ComfyUI |
| 58 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-flux1-schnell`: contains the checkpoint, text encoders and VAE for [FLUX.1 schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell) |
| 59 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-flux1-dev`: contains the checkpoint, text encoders and VAE for [FLUX.1 dev](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
| 60 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-sdxl`: contains the checkpoint and VAE for [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) |
| 61 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-sd3`: contains the checkpoint for [Stable Diffusion 3 medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium) |
62 | 62 | - ℹ️ [Use the Docker image on RunPod](#use-the-docker-image-on-runpod)
|
63 | 63 | - 🧪 Pick an [example workflow](./test_resources/workflows/) & [send it to your deployed endpoint](#interact-with-your-runpod-api)
|
64 | 64 |
|
|
70 | 70 | - Returned as base64-encoded string (default)
|
71 | 71 | - Uploaded to AWS S3 ([if AWS S3 is configured](#upload-image-to-aws-s3))
|
72 | 72 | - There are a few different Docker images to choose from:
|
73 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-flux1-schnell`: contains the [flux1-schnell.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-schnell) checkpoint, the [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors) + [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors) text encoders and [ae.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors) VAE for FLUX.1-schnell |
74 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-flux1-dev`: contains the [flux1-dev.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-dev) checkpoint, the [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors) + [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors) text encoders and [ae.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors) VAE for FLUX.1-dev |
75 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-sdxl`: contains the checkpoints and VAE for Stable Diffusion XL |
| 73 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-flux1-schnell`: contains the [flux1-schnell.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-schnell) checkpoint, the [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors) + [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors) text encoders and [ae.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors) VAE for FLUX.1-schnell |
| 74 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-flux1-dev`: contains the [flux1-dev.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-dev) checkpoint, the [clip_l.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors) + [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors) text encoders and [ae.safetensors](https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/main/ae.safetensors) VAE for FLUX.1-dev |
| 75 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-sdxl`: contains the checkpoints and VAE for Stable Diffusion XL |
76 | 76 | - Checkpoint: [sd_xl_base_1.0.safetensors](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
|
77 | 77 | - VAEs:
|
78 | 78 | - [sdxl_vae.safetensors](https://huggingface.co/stabilityai/sdxl-vae/)
|
79 | 79 | - [sdxl-vae-fp16-fix](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix/)
|
80 |
| - - `timpietruskyblibla/runpod-worker-comfy:3.4.0-sd3`: contains the [sd3_medium_incl_clips_t5xxlfp8.safetensors](https://huggingface.co/stabilityai/stable-diffusion-3-medium) checkpoint for Stable Diffusion 3 medium |
| 80 | + - `timpietruskyblibla/runpod-worker-comfy:3.5.0-sd3`: contains the [sd3_medium_incl_clips_t5xxlfp8.safetensors](https://huggingface.co/stabilityai/stable-diffusion-3-medium) checkpoint for Stable Diffusion 3 medium |
81 | 81 | - [Bring your own models](#bring-your-own-models)
|
82 | 82 | - Based on [Ubuntu + NVIDIA CUDA](https://hub.docker.com/r/nvidia/cuda)
|
83 | 83 |
|
@@ -113,7 +113,7 @@ This is only needed if you want to upload the generated picture to AWS S3. If yo
|
113 | 113 | - In the dialog, configure:
|
114 | 114 | - Template Name: `runpod-worker-comfy` (it can be anything you want)
|
115 | 115 | - Template Type: serverless (change template type to "serverless")
|
116 |
| - - Container Image: `<dockerhub_username>/<repository_name>:tag`, in this case: `timpietruskyblibla/runpod-worker-comfy:3.4.0-sd3` (or `-base` for a clean image or `-sdxl` for Stable Diffusion XL or `-flex1-schnell` for FLUX.1 schnell) |
| 116 | + - Container Image: `<dockerhub_username>/<repository_name>:tag`, in this case: `timpietruskyblibla/runpod-worker-comfy:3.5.0-sd3` (or `-base` for a clean image or `-sdxl` for Stable Diffusion XL or `-flex1-schnell` for FLUX.1 schnell) |
117 | 117 | - Container Registry Credentials: You can leave everything as it is, as this repo is public
|
118 | 118 | - Container Disk: `20 GB`
|
119 | 119 | - (optional) Environment Variables: [Configure S3](#upload-image-to-aws-s3)
|
|
0 commit comments