1.0.0 (2025-01-26)

Bug Fixes

added missing start command (9a7ffdb)
check_server default values for delay and check-interval (4945a9d)
convert environment variables to int (#70) (7ab3d2a)
create directories which are required to run ComfyUI (#58) (6edf62b)
don’t persist credentials (1546420)
don't run ntpdate as this is not working in GitHub Actions (2f7bd3f)
fixed the syntax error (ac3dddb)
fixed typo for ipadatper (5d7c166)
got rid of syntax error (c04de4d)
images in subfolders are not working, fixes #12 (37480c2)
path should be "loras" and not "lora" (8e579f6)
put snapshot file in the right place (69be408)
removed xl_more_art-full_v1 because civitai requires login now (2e8e638)
return the output of "process_output_image" and access jobId correctly (#11) (dc655ea)
semantic-release: added .releaserc (#21) (12b763d)
start the container in all cases (413707b)
update the version inside of semanticrelease (d93e991)
updated path to "comfyui" (37f66d0)
use custom GITHUB_TOKEN to bypass branch protection (9b6468a)

Features

added default ComfyUI workflow (fa6c385)
added FLUX.1 schnell & dev (9170191)
added runpod as local dependency (9deae9f)
added sensible defaults and default platform (3f5162a)
added unit tests for everthing, refactored the code to make it better testable, added test images (a7492ec)
added xl_more_art-full_v1, improved comments (9aea8ab)
automatically update latest version (7d846e8)
base64 image output (#8) (76bf0b1)
build ipadater only (d839c40)
example on how to configure the .env (4ed5296)
image-input, renamed "prompt" to "workflow", added "REFRESH_WORKER" (#14) (5f5e390)
logs should be written to stdout so that we can see them inside the worker (fc731ff)
network-volume; execution time config; skip default images; access ComfyUI via web (#35) (070cde5), closes #16
remove sdxl and flux1-schnell. add ipadapter (89122f5)
run the worker locally (#19) (34eb32b)
simplified and added compatibility with Windows (9f41231)
simplified input (35c2341)
simplified input to just have "prompt", removed unused code (0c3ccda)
support ipadapter (cd8b9da)
support sd3 (#46) (dde69d6)
updated path to "comfyui", added "ntpdate" to have the time of the container in sync with AWS (2fda578)
use local ".env" to load env variables, mount "comfyui/output" to localhost so that people can see the generated images (aa645a2)
use models from huggingface, not from local folder (b1af369)
wait until server is ready, wait until image generation is done, upload to s3 (ecfec13)

BREAKING CHANGES

we have 3 different images now instead of just one: base, sdxl and sd3
ci: use branch name for creating dev releases
ci: replace "/" with "-" to have a valid tag name
ci: correctly handle the tag name
ci: build an image that contains sd3 using docker bake
ci: use "set" instead of "args"
ci: use "env" instead of "set"
ci: use variables instead of args
ci: set variables directly for the targets
ci: write the secrets into the GITHUB_ENV
ci: handle env variables correctly
ci: use env variables from GitHub Variables
ci: added back to env
ci: print out env
ci: adding the vars directly into the workflow
ci: example workflow for sd3
ci: renamed DOCKERHUB_REPO to DOCKERHUB_REPOSITORY
ci: removed quotes for DOCKERHUB_REPOSITORY
ci: only use DOCKERHUB_REPO in bake
ci: added vars into sd3 target
ci: added direct target
ci: back to basics
ci: multi-stage build to not expose the HUGGINGFACE_ACCESS_TOKEN
ci: write everything into GITHUB_ENV again
ci: use correct name for final stage
ci: use correct runner
fix: make sure to use the latest versions of all packages
ci: simplified variables for all targets
docs: added 3 images, updated build your own image
docs: updated TOC
ci: updated name
ci: use docker bake to publish 3 images instead of just 1

1.0.0 (2025-01-24)

Bug Fixes

added missing start command (9a7ffdb)
check_server default values for delay and check-interval (4945a9d)
convert environment variables to int (#70) (7ab3d2a)
create directories which are required to run ComfyUI (#58) (6edf62b)
don’t persist credentials (1546420)
don't run ntpdate as this is not working in GitHub Actions (2f7bd3f)
fixed the syntax error (ac3dddb)
fixed typo for ipadatper (5d7c166)
got rid of syntax error (c04de4d)
images in subfolders are not working, fixes #12 (37480c2)
path should be "loras" and not "lora" (8e579f6)
put snapshot file in the right place (69be408)
removed xl_more_art-full_v1 because civitai requires login now (2e8e638)
return the output of "process_output_image" and access jobId correctly (#11) (dc655ea)
semantic-release: added .releaserc (#21) (12b763d)
start the container in all cases (413707b)
update the version inside of semanticrelease (d93e991)
updated path to "comfyui" (37f66d0)
use custom GITHUB_TOKEN to bypass branch protection (9b6468a)

Features

added default ComfyUI workflow (fa6c385)
added FLUX.1 schnell & dev (9170191)
added runpod as local dependency (9deae9f)
added sensible defaults and default platform (3f5162a)
added unit tests for everthing, refactored the code to make it better testable, added test images (a7492ec)
added xl_more_art-full_v1, improved comments (9aea8ab)
automatically update latest version (7d846e8)
base64 image output (#8) (76bf0b1)
example on how to configure the .env (4ed5296)
image-input, renamed "prompt" to "workflow", added "REFRESH_WORKER" (#14) (5f5e390)
logs should be written to stdout so that we can see them inside the worker (fc731ff)
network-volume; execution time config; skip default images; access ComfyUI via web (#35) (070cde5), closes #16
remove sdxl and flux1-schnell. add ipadapter (89122f5)
run the worker locally (#19) (34eb32b)
simplified and added compatibility with Windows (9f41231)
simplified input (35c2341)
simplified input to just have "prompt", removed unused code (0c3ccda)
support ipadapter (cd8b9da)
support sd3 (#46) (dde69d6)
updated path to "comfyui", added "ntpdate" to have the time of the container in sync with AWS (2fda578)
use local ".env" to load env variables, mount "comfyui/output" to localhost so that people can see the generated images (aa645a2)
use models from huggingface, not from local folder (b1af369)
wait until server is ready, wait until image generation is done, upload to s3 (ecfec13)

BREAKING CHANGES

we have 3 different images now instead of just one: base, sdxl and sd3
ci: use branch name for creating dev releases
ci: replace "/" with "-" to have a valid tag name
ci: correctly handle the tag name
ci: build an image that contains sd3 using docker bake
ci: use "set" instead of "args"
ci: use "env" instead of "set"
ci: use variables instead of args
ci: set variables directly for the targets
ci: write the secrets into the GITHUB_ENV
ci: handle env variables correctly
ci: use env variables from GitHub Variables
ci: added back to env
ci: print out env
ci: adding the vars directly into the workflow
ci: example workflow for sd3
ci: renamed DOCKERHUB_REPO to DOCKERHUB_REPOSITORY
ci: removed quotes for DOCKERHUB_REPOSITORY
ci: only use DOCKERHUB_REPO in bake
ci: added vars into sd3 target
ci: added direct target
ci: back to basics
ci: multi-stage build to not expose the HUGGINGFACE_ACCESS_TOKEN
ci: write everything into GITHUB_ENV again
ci: use correct name for final stage
ci: use correct runner
fix: make sure to use the latest versions of all packages
ci: simplified variables for all targets
docs: added 3 images, updated build your own image
docs: updated TOC
ci: updated name
ci: use docker bake to publish 3 images instead of just 1

1.0.0 (2025-01-24)

Bug Fixes

added missing start command (9a7ffdb)
check_server default values for delay and check-interval (4945a9d)
convert environment variables to int (#70) (7ab3d2a)
create directories which are required to run ComfyUI (#58) (6edf62b)
don’t persist credentials (1546420)
don't run ntpdate as this is not working in GitHub Actions (2f7bd3f)
fixed the syntax error (ac3dddb)
got rid of syntax error (c04de4d)
images in subfolders are not working, fixes #12 (37480c2)
path should be "loras" and not "lora" (8e579f6)
put snapshot file in the right place (69be408)
removed xl_more_art-full_v1 because civitai requires login now (2e8e638)
return the output of "process_output_image" and access jobId correctly (#11) (dc655ea)
semantic-release: added .releaserc (#21) (12b763d)
start the container in all cases (413707b)
update the version inside of semanticrelease (d93e991)
updated path to "comfyui" (37f66d0)
use custom GITHUB_TOKEN to bypass branch protection (9b6468a)

Features

added default ComfyUI workflow (fa6c385)
added FLUX.1 schnell & dev (9170191)
added runpod as local dependency (9deae9f)
added sensible defaults and default platform (3f5162a)
added unit tests for everthing, refactored the code to make it better testable, added test images (a7492ec)
added xl_more_art-full_v1, improved comments (9aea8ab)
automatically update latest version (7d846e8)
base64 image output (#8) (76bf0b1)
example on how to configure the .env (4ed5296)
image-input, renamed "prompt" to "workflow", added "REFRESH_WORKER" (#14) (5f5e390)
logs should be written to stdout so that we can see them inside the worker (fc731ff)
network-volume; execution time config; skip default images; access ComfyUI via web (#35) (070cde5), closes #16
remove sdxl and flux1-schnell. add ipadapter (89122f5)
run the worker locally (#19) (34eb32b)
simplified and added compatibility with Windows (9f41231)
simplified input (35c2341)
simplified input to just have "prompt", removed unused code (0c3ccda)
support ipadapter (cd8b9da)
support sd3 (#46) (dde69d6)
updated path to "comfyui", added "ntpdate" to have the time of the container in sync with AWS (2fda578)
use local ".env" to load env variables, mount "comfyui/output" to localhost so that people can see the generated images (aa645a2)
use models from huggingface, not from local folder (b1af369)
wait until server is ready, wait until image generation is done, upload to s3 (ecfec13)

BREAKING CHANGES

we have 3 different images now instead of just one: base, sdxl and sd3
ci: use branch name for creating dev releases
ci: replace "/" with "-" to have a valid tag name
ci: correctly handle the tag name
ci: build an image that contains sd3 using docker bake
ci: use "set" instead of "args"
ci: use "env" instead of "set"
ci: use variables instead of args
ci: set variables directly for the targets
ci: write the secrets into the GITHUB_ENV
ci: handle env variables correctly
ci: use env variables from GitHub Variables
ci: added back to env
ci: print out env
ci: adding the vars directly into the workflow
ci: example workflow for sd3
ci: renamed DOCKERHUB_REPO to DOCKERHUB_REPOSITORY
ci: removed quotes for DOCKERHUB_REPOSITORY
ci: only use DOCKERHUB_REPO in bake
ci: added vars into sd3 target
ci: added direct target
ci: back to basics
ci: multi-stage build to not expose the HUGGINGFACE_ACCESS_TOKEN
ci: write everything into GITHUB_ENV again
ci: use correct name for final stage
ci: use correct runner
fix: make sure to use the latest versions of all packages
ci: simplified variables for all targets
docs: added 3 images, updated build your own image
docs: updated TOC
ci: updated name
ci: use docker bake to publish 3 images instead of just 1

1.0.0 (2025-01-24)

Bug Fixes

added missing start command (9a7ffdb)
check_server default values for delay and check-interval (4945a9d)
convert environment variables to int (#70) (7ab3d2a)
create directories which are required to run ComfyUI (#58) (6edf62b)
don’t persist credentials (1546420)
don't run ntpdate as this is not working in GitHub Actions (2f7bd3f)
got rid of syntax error (c04de4d)
images in subfolders are not working, fixes #12 (37480c2)
path should be "loras" and not "lora" (8e579f6)
put snapshot file in the right place (69be408)
removed xl_more_art-full_v1 because civitai requires login now (2e8e638)
return the output of "process_output_image" and access jobId correctly (#11) (dc655ea)
semantic-release: added .releaserc (#21) (12b763d)
start the container in all cases (413707b)
update the version inside of semanticrelease (d93e991)
updated path to "comfyui" (37f66d0)
use custom GITHUB_TOKEN to bypass branch protection (9b6468a)

Features

added default ComfyUI workflow (fa6c385)
added FLUX.1 schnell & dev (9170191)
added runpod as local dependency (9deae9f)
added sensible defaults and default platform (3f5162a)
added unit tests for everthing, refactored the code to make it better testable, added test images (a7492ec)
added xl_more_art-full_v1, improved comments (9aea8ab)
automatically update latest version (7d846e8)
base64 image output (#8) (76bf0b1)
example on how to configure the .env (4ed5296)
image-input, renamed "prompt" to "workflow", added "REFRESH_WORKER" (#14) (5f5e390)
logs should be written to stdout so that we can see them inside the worker (fc731ff)
network-volume; execution time config; skip default images; access ComfyUI via web (#35) (070cde5), closes #16
remove sdxl and flux1-schnell. add ipadapter (89122f5)
run the worker locally (#19) (34eb32b)
simplified and added compatibility with Windows (9f41231)
simplified input (35c2341)
simplified input to just have "prompt", removed unused code (0c3ccda)
support ipadapter (cd8b9da)
support sd3 (#46) (dde69d6)
updated path to "comfyui", added "ntpdate" to have the time of the container in sync with AWS (2fda578)
use local ".env" to load env variables, mount "comfyui/output" to localhost so that people can see the generated images (aa645a2)
use models from huggingface, not from local folder (b1af369)
wait until server is ready, wait until image generation is done, upload to s3 (ecfec13)

BREAKING CHANGES

we have 3 different images now instead of just one: base, sdxl and sd3
ci: use branch name for creating dev releases
ci: replace "/" with "-" to have a valid tag name
ci: correctly handle the tag name
ci: build an image that contains sd3 using docker bake
ci: use "set" instead of "args"
ci: use "env" instead of "set"
ci: use variables instead of args
ci: set variables directly for the targets
ci: write the secrets into the GITHUB_ENV
ci: handle env variables correctly
ci: use env variables from GitHub Variables
ci: added back to env
ci: print out env
ci: adding the vars directly into the workflow
ci: example workflow for sd3
ci: renamed DOCKERHUB_REPO to DOCKERHUB_REPOSITORY
ci: removed quotes for DOCKERHUB_REPOSITORY
ci: only use DOCKERHUB_REPO in bake
ci: added vars into sd3 target
ci: added direct target
ci: back to basics
ci: multi-stage build to not expose the HUGGINGFACE_ACCESS_TOKEN
ci: write everything into GITHUB_ENV again
ci: use correct name for final stage
ci: use correct runner
fix: make sure to use the latest versions of all packages
ci: simplified variables for all targets
docs: added 3 images, updated build your own image
docs: updated TOC
ci: updated name
ci: use docker bake to publish 3 images instead of just 1

1.0.0 (2025-01-24)

Bug Fixes

added missing start command (9a7ffdb)
check_server default values for delay and check-interval (4945a9d)
convert environment variables to int (#70) (7ab3d2a)
create directories which are required to run ComfyUI (#58) (6edf62b)
don’t persist credentials (1546420)
don't run ntpdate as this is not working in GitHub Actions (2f7bd3f)
got rid of syntax error (c04de4d)
images in subfolders are not working, fixes #12 (37480c2)
path should be "loras" and not "lora" (8e579f6)
put snapshot file in the right place (69be408)
removed xl_more_art-full_v1 because civitai requires login now (2e8e638)
return the output of "process_output_image" and access jobId correctly (#11) (dc655ea)
semantic-release: added .releaserc (#21) (12b763d)
start the container in all cases (413707b)
update the version inside of semanticrelease (d93e991)
updated path to "comfyui" (37f66d0)
use custom GITHUB_TOKEN to bypass branch protection (9b6468a)

Features

added default ComfyUI workflow (fa6c385)
added FLUX.1 schnell & dev (9170191)
added runpod as local dependency (9deae9f)
added sensible defaults and default platform (3f5162a)
added unit tests for everthing, refactored the code to make it better testable, added test images (a7492ec)
added xl_more_art-full_v1, improved comments (9aea8ab)
automatically update latest version (7d846e8)
base64 image output (#8) (76bf0b1)
example on how to configure the .env (4ed5296)
image-input, renamed "prompt" to "workflow", added "REFRESH_WORKER" (#14) (5f5e390)
logs should be written to stdout so that we can see them inside the worker (fc731ff)
network-volume; execution time config; skip default images; access ComfyUI via web (#35) (070cde5), closes #16
remove sdxl and flux1-schnell. add ipadapter (89122f5)
run the worker locally (#19) (34eb32b)
simplified and added compatibility with Windows (9f41231)
simplified input (35c2341)
simplified input to just have "prompt", removed unused code (0c3ccda)
support ipadapter (cd8b9da)
support sd3 (#46) (dde69d6)
updated path to "comfyui", added "ntpdate" to have the time of the container in sync with AWS (2fda578)
use local ".env" to load env variables, mount "comfyui/output" to localhost so that people can see the generated images (aa645a2)
use models from huggingface, not from local folder (b1af369)
wait until server is ready, wait until image generation is done, upload to s3 (ecfec13)

BREAKING CHANGES

we have 3 different images now instead of just one: base, sdxl and sd3
ci: use branch name for creating dev releases
ci: replace "/" with "-" to have a valid tag name
ci: correctly handle the tag name
ci: build an image that contains sd3 using docker bake
ci: use "set" instead of "args"
ci: use "env" instead of "set"
ci: use variables instead of args
ci: set variables directly for the targets
ci: write the secrets into the GITHUB_ENV
ci: handle env variables correctly
ci: use env variables from GitHub Variables
ci: added back to env
ci: print out env
ci: adding the vars directly into the workflow
ci: example workflow for sd3
ci: renamed DOCKERHUB_REPO to DOCKERHUB_REPOSITORY
ci: removed quotes for DOCKERHUB_REPOSITORY
ci: only use DOCKERHUB_REPO in bake
ci: added vars into sd3 target
ci: added direct target
ci: back to basics
ci: multi-stage build to not expose the HUGGINGFACE_ACCESS_TOKEN
ci: write everything into GITHUB_ENV again
ci: use correct name for final stage
ci: use correct runner
fix: make sure to use the latest versions of all packages
ci: simplified variables for all targets
docs: added 3 images, updated build your own image
docs: updated TOC
ci: updated name
ci: use docker bake to publish 3 images instead of just 1

3.4.0 (2024-11-19)

Bug Fixes

start the container in all cases (413707b)

Features

simplified and added compatibility with Windows (9f41231)

3.3.0 (2024-11-18)

Bug Fixes

added missing start command (9a7ffdb)

Features

added sensible defaults and default platform (3f5162a)

3.2.1 (2024-11-18)

Bug Fixes

update the version inside of semanticrelease (d93e991)

3.2.0 (2024-11-18)

Features

automatically update latest version (7d846e8)

3.1.2 (2024-11-10)

Bug Fixes

convert environment variables to int (#70) (7ab3d2a)

3.1.1 (2024-11-10)

Bug Fixes

create directories which are required to run ComfyUI (#58) (6edf62b)

3.1.0 (2024-08-19)

Features

added FLUX.1 schnell & dev (9170191)

3.0.0 (2024-07-26)

Features

support sd3 (#46) (dde69d6)
provide a base image (#41)

BREAKING CHANGES

we have 3 different images now instead of just one:
- timpietruskyblibla/runpod-worker-comfy:3.0.0-base: doesn't contain any checkpoints, just a clean ComfyUI image
- timpietruskyblibla/runpod-worker-comfy:3.0.0-sdxl: contains the checkpoints and VAE for Stable Diffusion XL
  - Checkpoint: sd_xl_base_1.0.safetensors
  - VAEs:
    - sdxl_vae.safetensors
    - sdxl-vae-fp16-fix
- timpietruskyblibla/runpod-worker-comfy:3.0.0-sd3: contains the sd3_medium_incl_clips_t5xxlfp8.safetensors checkpoint for Stable Diffusion 3
latest will not be updated anymore
every branch gets their own 3 images deployed automatically to Docker Hub

2.2.0 (2024-06-04)

Bug Fixes

don’t persist credentials (1546420)
use custom GITHUB_TOKEN to bypass branch protection (9b6468a)

Features

network-volume; execution time config; skip default images; access ComfyUI via web (#35) (070cde5), closes #16

2.1.3 (2024-05-28)

Bug Fixes

images in subfolders are not working, fixes #12 (37480c2)

2.1.2 (2024-05-27)

Bug Fixes

removed xl_more_art-full_v1 because civitai requires login now (2e8e638)

2.1.1 (2024-05-27)

Bug Fixes

check_server default values for delay and check-interval (4945a9d)

2.1.0 (2024-02-12)

Bug Fixes

semantic-release: added .releaserc (#21) (12b763d)

Features

run the worker locally (#19) (34eb32b)

(2023-11-18)

1.1.1 (2023-11-17)

Bug Fixes

return the output of "process_output_image" and access jobId correctly (#11) (dc655ea)

1.1.0 (2023-11-17)

Bug Fixes

path should be "loras" and not "lora" (8e579f6)

Features

added unit tests for everthing, refactored the code to make it better testable, added test images (a7492ec)
added xl_more_art-full_v1, improved comments (9aea8ab)
base64 image output (#8) (76bf0b1)

1.0.0 (2023-10-12)

Bug Fixes

don't run ntpdate as this is not working in GitHub Actions (2f7bd3f)
got rid of syntax error (c04de4d)
updated path to "comfyui" (37f66d0)

Features

added default ComfyUI workflow (fa6c385)
added runpod as local dependency (9deae9f)
example on how to configure the .env (4ed5296)
logs should be written to stdout so that we can see them inside the worker (fc731ff)
simplified input (35c2341)
simplified input to just have "prompt", removed unused code (0c3ccda)
updated path to "comfyui", added "ntpdate" to have the time of the container in sync with AWS (2fda578)
use local ".env" to load env variables, mount "comfyui/output" to localhost so that people can see the generated images (aa645a2)
use models from huggingface, not from local folder (b1af369)
wait until server is ready, wait until image generation is done, upload to s3 (ecfec13)

Files

CHANGELOG.md

Latest commit

History

CHANGELOG.md

File metadata and controls

1.0.0 (2025-01-26)

Bug Fixes

Features

BREAKING CHANGES

1.0.0 (2025-01-24)

Bug Fixes

Features

BREAKING CHANGES

1.0.0 (2025-01-24)

Bug Fixes

Features

BREAKING CHANGES

1.0.0 (2025-01-24)

Bug Fixes

Features

BREAKING CHANGES

1.0.0 (2025-01-24)

Bug Fixes

Features

BREAKING CHANGES

3.4.0 (2024-11-19)

Bug Fixes

Features

3.3.0 (2024-11-18)

Bug Fixes

Features

3.2.1 (2024-11-18)

Bug Fixes

3.2.0 (2024-11-18)

Features

3.1.2 (2024-11-10)

Bug Fixes

3.1.1 (2024-11-10)

Bug Fixes

3.1.0 (2024-08-19)

Features

3.0.0 (2024-07-26)

Features

BREAKING CHANGES

2.2.0 (2024-06-04)

Bug Fixes

Features

2.1.3 (2024-05-28)

Bug Fixes

2.1.2 (2024-05-27)

Bug Fixes

2.1.1 (2024-05-27)

Bug Fixes

2.1.0 (2024-02-12)

Bug Fixes

Features

(2023-11-18)

1.1.1 (2023-11-17)

Bug Fixes

1.1.0 (2023-11-17)

Bug Fixes

Features

1.0.0 (2023-10-12)

Bug Fixes

Features