You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
-`timpietruskyblibla/runpod-worker-comfy:3.0.0-sd3`: contains the [sd3_medium_incl_clips_t5xxlfp8.safetensors](https://huggingface.co/stabilityai/stable-diffusion-3-medium) checkpoint for Stable Diffusion 3
55
+
- 🐳 Choose one of the five available images for your serverless endpoint:
56
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-base`: doesn't contain anything, just a clean ComfyUI
57
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-flux1-schnell`: contains the checkpoint, text encoders and VAE for [FLUX.1 schnell](https://huggingface.co/black-forest-labs/FLUX.1-schnell)
58
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-flux1-dev`: contains the checkpoint, text encoders and VAE for [FLUX.1 dev](https://huggingface.co/black-forest-labs/FLUX.1-dev)
59
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-sdxl`: contains the checkpoint and VAE for [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
60
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-sd3`: contains the checkpoint for [Stable Diffusion 3 medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium)
60
61
- ℹ️ [Use the Docker image on RunPod](#use-the-docker-image-on-runpod)
62
+
- 🧪 Pick an [example workflow](./test_resources/workflows/) & [send it to your deployed endpoint](#interact-with-your-runpod-api)
- Uploaded to AWS S3 ([if AWS S3 is configured](#upload-image-to-aws-s3))
69
-
- There are three different Docker images to choose from:
70
-
-`timpietruskyblibla/runpod-worker-comfy:3.0.0-base`: doesn't contain anything, just a clean ComfyUI
71
-
-`timpietruskyblibla/runpod-worker-comfy:3.0.0-sdxl`: contains the checkpoint and VAE for Stable Diffusion XL
72
-
-`timpietruskyblibla/runpod-worker-comfy:3.0.0-sd3`: contains the checkpoint for Stable Diffusion 3
71
+
- There are a few different Docker images to choose from:
72
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-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
73
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-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
74
+
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-sdxl`: contains the checkpoints and VAE for Stable Diffusion XL
-`timpietruskyblibla/runpod-worker-comfy:3.1.0-sd3`: contains the [sd3_medium_incl_clips_t5xxlfp8.safetensors](https://huggingface.co/stabilityai/stable-diffusion-3-medium) checkpoint for Stable Diffusion 3 medium
73
80
-[Bring your own models](#bring-your-own-models)
74
81
- Based on [Ubuntu + NVIDIA CUDA](https://hub.docker.com/r/nvidia/cuda)
75
82
@@ -99,30 +106,46 @@ This is only needed if you want to upload the generated picture to AWS S3. If yo
99
106
100
107
## Use the Docker image on RunPod
101
108
109
+
### Create your template (optional)
110
+
102
111
- Create a [new template](https://runpod.io/console/serverless/user/templates) by clicking on `New Template`
103
112
- In the dialog, configure:
104
113
- Template Name: `runpod-worker-comfy` (it can be anything you want)
105
114
- Template Type: serverless (change template type to "serverless")
106
-
- Container Image: `<dockerhub_username>/<repository_name>:tag`, in this case: `timpietruskyblibla/runpod-worker-comfy:3.0.0-sd3` (or `-base` for a clean image or `-sdxl` for Stable Diffusion XL)
115
+
- Container Image: `<dockerhub_username>/<repository_name>:tag`, in this case: `timpietruskyblibla/runpod-worker-comfy:3.1.0-sd3` (or `-base` for a clean image or `-sdxl` for Stable Diffusion XL or `-flex1-schnell` for FLUX.1 schnell)
107
116
- Container Registry Credentials: You can leave everything as it is, as this repo is public
- Note: You can also not configure it, the images will then stay in the worker. In order to have them stored permanently, [we have to add the network volume](https://github.com/blib-la/runpod-worker-comfy/issues/1)
111
120
- Click on `Save Template`
121
+
122
+
### Create your endpoint
123
+
112
124
- Navigate to [`Serverless > Endpoints`](https://www.runpod.io/console/serverless/user/endpoints) and click on `New Endpoint`
113
125
- In the dialog, configure:
126
+
114
127
- Endpoint Name: `comfy`
115
-
-Select Template: `runpod-worker-comfy` (or whatever name you gave your template)
128
+
-Worker configuration: Select a GPU that can run the model you have chosen (see [GPU recommendations](#gpu-recommendations))
116
129
- Active Workers: `0` (whatever makes sense for you)
117
130
- Max Workers: `3` (whatever makes sense for you)
131
+
- GPUs/Worker: `1`
118
132
- Idle Timeout: `5` (you can leave the default)
119
133
- Flash Boot: `enabled` (doesn't cost more, but provides faster boot of our worker, which is good)
134
+
- Select Template: `runpod-worker-comfy` (or whatever name you gave your template)
120
135
- (optional) Advanced: If you are using a Network Volume, select it under `Select Network Volume`. Otherwise leave the defaults.
121
-
- Select a GPU that has some availability
122
-
- GPUs/Worker: `1`
136
+
123
137
- Click `deploy`
124
138
- Your endpoint will be created, you can click on it to see the dashboard
The following describes which fields exist when doing requests to the API. We only describe the fields that are sent via `input` as those are needed by the worker itself. For a full list of fields, please take a look at the [official documentation](https://docs.runpod.io/docs/serverless-usage).
@@ -193,7 +216,7 @@ The API expects a [JSON in this form](#json-request-body), where `workflow` is t
193
216
194
217
Please also take a look at the [test_input.json](./test_input.json) to see how the API input should look like.
0 commit comments