image-with-comfyui
Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like "make a picture of", "replace the background", "cut out / extract the subject of", "turn this into a video", "edit my photo", or &quo
as observed 2026-11-06T15:44:01.875Z- Identifier
image-with-comfyui- Source
- ClawHub
- Version observed
- 4.7.5
- Source repository
- not published
- Repository observation
- No source repository listed
- First observed here
- 2026-08-28T22:06:26.689Z
- Observations recorded
- 16
- Installs (reported upstream)
- 24
- Weekly downloads (upstream)
- 2,504
- Declared license
- MIT-0
Observation history
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"all-or-nothing safety fix for Hunyuan/I2M extraction; retains server copies on extraction failure" | "- Updated the skill version to 4.7.5.\n- Removed `skill-card.md`." |
latestVersion |
"4.7.2" | "4.7.5" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"- Added all-or-nothing server cleanup: purge only after every required output is safely saved locally; otherwise server copies remain available for retry.\n- Purge attempts are re | "all-or-nothing safety fix for Hunyuan/I2M extraction; retains server copies on extraction failure" |
latestVersion |
"4.6.9" | "4.7.2" |
summary |
"Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / | "Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"- Added a permissions and data-flow declaration describing the skill’s environment, network, and filesystem access, plus its lack of persistence.\n- Removed `skill-card.md`.\n- Up | "- Added all-or-nothing server cleanup: purge only after every required output is safely saved locally; otherwise server copies remain available for retry.\n- Purge attempts are re |
latestVersion |
"4.6.1" | "4.6.9" |
summary |
"Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / | "Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"- Updated the minimum server requirement for the optional retrieve-then-purge plugin: ComfyUI 0.38 or later is needed.\n- Added LICENSE and VERSION files; removed skill-card.md." | "- Added a permissions and data-flow declaration describing the skill’s environment, network, and filesystem access, plus its lack of persistence.\n- Removed `skill-card.md`.\n- Up |
latestVersion |
"4.5.7" | "4.6.1" |
summary |
"Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / | "Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Improved agent guidance by consolidating functionality into the script, eliminating manual agent operations. Improved result retrieval accuracy (unique tagid stamped into every ou | "- Updated the minimum server requirement for the optional retrieve-then-purge plugin: ComfyUI 0.38 or later is needed.\n- Added LICENSE and VERSION files; removed skill-card.md." |
latestVersion |
"4.1.0" | "4.5.7" |
summary |
"Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / | "Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Add MiniMax H3 (FastH3 v2) video workflows (t2v + i2v) with audio-enabled video generation, as default 2v. Docs + source tables updated. v3.8.0 -> v4.0.0." | "Improved agent guidance by consolidating functionality into the script, eliminating manual agent operations. Improved result retrieval accuracy (unique tagid stamped into every ou |
latestVersion |
"4.0.0" | "4.1.0" |
summary |
"Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script | "Use to generate, edit, or animate images and videos through a configured ComfyUI server — trigger with requests like \"make a picture of\", \"replace the background\", \"cut out / |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Added Qwen-Image 2.1 Turbo (qwen21t) as the default model for both text-to-image and image-to-image, making image generation faster. Includes the new turbo workflow, output filena | "Add MiniMax H3 (FastH3 v2) video workflows (t2v + i2v) with audio-enabled video generation, as default 2v. Docs + source tables updated. v3.8.0 -> v4.0.0." |
latestVersion |
"3.7.0" | "4.0.0" |
summary |
"Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script | "Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Added documentation that Qwen-Image 2.1 can cut out / extract the subject or any image element into a transparent-background image." | "Added Qwen-Image 2.1 Turbo (qwen21t) as the default model for both text-to-image and image-to-image, making image generation faster. Includes the new turbo workflow, output filena |
latestVersion |
"3.6.0" | "3.7.0" |
summary |
"Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script | "Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"Fixed workspace directory detection so output files land on the correct standard path." | "Added documentation that Qwen-Image 2.1 can cut out / extract the subject or any image element into a transparent-background image." |
latestVersion |
"3.5.1" | "3.6.0" |
summary |
"Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script | "Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"Add reference to the sunshinejnjn/comfyui-auth custom node for Bearer API key auth; version bump to 3.5.0" | "Fixed workspace directory detection so output files land on the correct standard path." |
latestVersion |
"3.5.0" | "3.5.1" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.2.0: i2m delivery scaling. The Hunyuan 3D v2.1 GLB comes out at a normalized unit scale (character ~2 units, no declared units), so the script now scales the GLB in place by a | "Add reference to the sunshinejnjn/comfyui-auth custom node for Bearer API key auth; version bump to 3.5.0" |
latestVersion |
"3.2.0" | "3.5.0" |
Fields that differed: changelog latestVersion
| Field | Before | After |
|---|---|---|
changelog |
"v3.0.0: new i2m mode — image → 3D mesh via Hunyuan 3D v2.1 (GLB). Auto-extracts the main character first (i2i transparent cutout by default, or --extract rembg / none), then runs | "v3.2.0: i2m delivery scaling. The Hunyuan 3D v2.1 GLB comes out at a normalized unit scale (character ~2 units, no declared units), so the script now scales the GLB in place by a |
latestVersion |
"3.0.0" | "3.2.0" |
Fields that differed: changelog latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v2.3.0: (1) unified output filename scheme — qwen21 t2i='qt2i', qwen21 i2i='qi2i', qwen_imageedit='qei2i', z-image='zt2i', sd35='st2i' + timestamp + counter; (2) trailing undersco | "v3.0.0: new i2m mode — image → 3D mesh via Hunyuan 3D v2.1 (GLB). Auto-extracts the main character first (i2i transparent cutout by default, or --extract rembg / none), then runs |
latestVersion |
"2.3.0" | "3.0.0" |
summary |
"Use to generate, edit, or animate images and videos through a ComfyUI server (loopback by default; remote only via an explicit, trusted COMFYUI_URL) — trigger with requests like \ | "Use to generate, edit, or animate images and videos through a user-defined ComfyUI server (COMFYUI_URL env var or comfyui_url in config.json; if no server is reachable the script |
Fields that differed: changelog displayName latestVersion summary
| Field | Before | After |
|---|---|---|
changelog |
"v1.7.1: ClawHub security audit remediation. (HIGH) Bundled config.json default endpoint changed from a private-network LAN address to loopback-only http://127.0.0.1:8188; non-loop | "v2.3.0: (1) unified output filename scheme — qwen21 t2i='qt2i', qwen21 i2i='qi2i', qwen_imageedit='qei2i', z-image='zt2i', sd35='st2i' + timestamp + counter; (2) trailing undersco |
displayName |
"Image With Comfyui" | "image-with-comfyui" |
latestVersion |
"1.7.1" | "2.3.0" |
summary |
"Call a local ComfyUI instance for text-to-image (T2I), image-to-image/edit (I2I), and image-to-video (I2V) generation. Supports Z-Image, SD3.5 Medium, Qwen I..." | "Use to generate, edit, or animate images and videos through a ComfyUI server (loopback by default; remote only via an explicit, trusted COMFYUI_URL) — trigger with requests like \ |
Fields that differed: license changelog latestVersion
| Field | Before | After |
|---|---|---|
license |
null | "MIT-0" |
changelog |
"Add trigger-phrase-rich description for better skill routing (e.g. 'make a picture of', 'replace the background', 'turn this into a video', 'edit my photo'). Description now surfa | "v1.7.1: ClawHub security audit remediation. (HIGH) Bundled config.json default endpoint changed from a private-network LAN address to loopback-only http://127.0.0.1:8188; non-loop |
latestVersion |
"1.7.0" | "1.7.1" |
Correction
If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.