Compare commits

...

5 Commits

Author SHA1 Message Date
Terry Jia
8822627a60 range type 2026-04-07 14:12:22 -04:00
huemin
b615af1c65 Add support for small flux.2 decoder (#13314) 2026-04-07 03:44:18 -04:00
comfyanonymous
40862c0776 Support Ace Step 1.5 XL model. (#13317) 2026-04-07 03:13:47 -04:00
Terry Jia
50076f3439 format blueprint (#13315)
Co-authored-by: guill <jacob.e.segal@gmail.com>
2026-04-06 23:33:55 -04:00
comfyanonymous
61c2387436 Ace step empty latent nodes follow intermediate dtype. (#13313) 2026-04-06 18:12:16 -07:00
47 changed files with 48950 additions and 50 deletions

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +1,322 @@
{"revision": 0, "last_node_id": 29, "last_link_id": 0, "nodes": [{"id": 29, "type": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "pos": [1970, -230], "size": [180, 86], "flags": {}, "order": 5, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": []}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": []}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": []}], "title": "Image Channels", "properties": {"proxyWidgets": []}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 28, "lastLinkId": 39, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Image Channels", "inputNode": {"id": -10, "bounding": [1820, -185, 120, 60]}, "outputNode": {"id": -20, "bounding": [2460, -215, 120, 120]}, "inputs": [{"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe", "name": "images.image0", "type": "IMAGE", "linkIds": [39], "localized_name": "images.image0", "label": "image", "pos": [1920, -165]}], "outputs": [{"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b", "name": "IMAGE0", "type": "IMAGE", "linkIds": [26], "localized_name": "IMAGE0", "label": "R", "pos": [2480, -195]}, {"id": "fb44a77e-0522-43e9-9527-82e7465b3596", "name": "IMAGE1", "type": "IMAGE", "linkIds": [27], "localized_name": "IMAGE1", "label": "G", "pos": [2480, -175]}, {"id": "81460ee6-0131-402a-874f-6bf3001fc4ff", "name": "IMAGE2", "type": "IMAGE", "linkIds": [28], "localized_name": "IMAGE2", "label": "B", "pos": [2480, -155]}, {"id": "ae690246-80d4-4951-b1d9-9306d8a77417", "name": "IMAGE3", "type": "IMAGE", "linkIds": [29], "localized_name": "IMAGE3", "label": "A", "pos": [2480, -135]}], "widgets": [], "nodes": [{"id": 23, "type": "GLSLShader", "pos": [2000, -330], "size": [400, 172], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 39}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}], "outputs": [{"label": "R", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [26]}, {"label": "G", "localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": [27]}, {"label": "B", "localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": [28]}, {"label": "A", "localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": [29]}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n", "from_input"]}], "groups": [], "links": [{"id": 39, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 26, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}, {"id": 27, "origin_id": 23, "origin_slot": 1, "target_id": -20, "target_slot": 1, "type": "IMAGE"}, {"id": 28, "origin_id": 23, "origin_slot": 2, "target_id": -20, "target_slot": 2, "type": "IMAGE"}, {"id": 29, "origin_id": 23, "origin_slot": 3, "target_id": -20, "target_slot": 3, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Color adjust"}]}}
{
"revision": 0,
"last_node_id": 29,
"last_link_id": 0,
"nodes": [
{
"id": 29,
"type": "4c9d6ea4-b912-40e5-8766-6793a9758c53",
"pos": [
1970,
-230
],
"size": [
180,
86
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"label": "image",
"localized_name": "images.image0",
"name": "images.image0",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"label": "R",
"localized_name": "IMAGE0",
"name": "IMAGE0",
"type": "IMAGE",
"links": []
},
{
"label": "G",
"localized_name": "IMAGE1",
"name": "IMAGE1",
"type": "IMAGE",
"links": []
},
{
"label": "B",
"localized_name": "IMAGE2",
"name": "IMAGE2",
"type": "IMAGE",
"links": []
},
{
"label": "A",
"localized_name": "IMAGE3",
"name": "IMAGE3",
"type": "IMAGE",
"links": []
}
],
"title": "Image Channels",
"properties": {
"proxyWidgets": []
},
"widgets_values": []
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "4c9d6ea4-b912-40e5-8766-6793a9758c53",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 28,
"lastLinkId": 39,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Image Channels",
"inputNode": {
"id": -10,
"bounding": [
1820,
-185,
120,
60
]
},
"outputNode": {
"id": -20,
"bounding": [
2460,
-215,
120,
120
]
},
"inputs": [
{
"id": "3522932b-2d86-4a1f-a02a-cb29f3a9d7fe",
"name": "images.image0",
"type": "IMAGE",
"linkIds": [
39
],
"localized_name": "images.image0",
"label": "image",
"pos": [
1920,
-165
]
}
],
"outputs": [
{
"id": "605cb9c3-b065-4d9b-81d2-3ec331889b2b",
"name": "IMAGE0",
"type": "IMAGE",
"linkIds": [
26
],
"localized_name": "IMAGE0",
"label": "R",
"pos": [
2480,
-195
]
},
{
"id": "fb44a77e-0522-43e9-9527-82e7465b3596",
"name": "IMAGE1",
"type": "IMAGE",
"linkIds": [
27
],
"localized_name": "IMAGE1",
"label": "G",
"pos": [
2480,
-175
]
},
{
"id": "81460ee6-0131-402a-874f-6bf3001fc4ff",
"name": "IMAGE2",
"type": "IMAGE",
"linkIds": [
28
],
"localized_name": "IMAGE2",
"label": "B",
"pos": [
2480,
-155
]
},
{
"id": "ae690246-80d4-4951-b1d9-9306d8a77417",
"name": "IMAGE3",
"type": "IMAGE",
"linkIds": [
29
],
"localized_name": "IMAGE3",
"label": "A",
"pos": [
2480,
-135
]
}
],
"widgets": [],
"nodes": [
{
"id": 23,
"type": "GLSLShader",
"pos": [
2000,
-330
],
"size": [
400,
172
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"label": "image",
"localized_name": "images.image0",
"name": "images.image0",
"type": "IMAGE",
"link": 39
},
{
"localized_name": "fragment_shader",
"name": "fragment_shader",
"type": "STRING",
"widget": {
"name": "fragment_shader"
},
"link": null
},
{
"localized_name": "size_mode",
"name": "size_mode",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "size_mode"
},
"link": null
},
{
"label": "image1",
"localized_name": "images.image1",
"name": "images.image1",
"shape": 7,
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"label": "R",
"localized_name": "IMAGE0",
"name": "IMAGE0",
"type": "IMAGE",
"links": [
26
]
},
{
"label": "G",
"localized_name": "IMAGE1",
"name": "IMAGE1",
"type": "IMAGE",
"links": [
27
]
},
{
"label": "B",
"localized_name": "IMAGE2",
"name": "IMAGE2",
"type": "IMAGE",
"links": [
28
]
},
{
"label": "A",
"localized_name": "IMAGE3",
"name": "IMAGE3",
"type": "IMAGE",
"links": [
29
]
}
],
"properties": {
"Node name for S&R": "GLSLShader"
},
"widgets_values": [
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\nlayout(location = 1) out vec4 fragColor1;\nlayout(location = 2) out vec4 fragColor2;\nlayout(location = 3) out vec4 fragColor3;\n\nvoid main() {\n vec4 color = texture(u_image0, v_texCoord);\n // Output each channel as grayscale to separate render targets\n fragColor0 = vec4(vec3(color.r), 1.0); // Red channel\n fragColor1 = vec4(vec3(color.g), 1.0); // Green channel\n fragColor2 = vec4(vec3(color.b), 1.0); // Blue channel\n fragColor3 = vec4(vec3(color.a), 1.0); // Alpha channel\n}\n",
"from_input"
]
}
],
"groups": [],
"links": [
{
"id": 39,
"origin_id": -10,
"origin_slot": 0,
"target_id": 23,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 26,
"origin_id": 23,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 27,
"origin_id": 23,
"origin_slot": 1,
"target_id": -20,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 28,
"origin_id": 23,
"origin_slot": 2,
"target_id": -20,
"target_slot": 2,
"type": "IMAGE"
},
{
"id": 29,
"origin_id": 23,
"origin_slot": 3,
"target_id": -20,
"target_slot": 3,
"type": "IMAGE"
}
],
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Color adjust"
}
]
}
}

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +1,278 @@
{"revision": 0, "last_node_id": 15, "last_link_id": 0, "nodes": [{"id": 15, "type": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", "pos": [-1490, 2040], "size": [400, 260], "flags": {}, "order": 0, "mode": 0, "inputs": [{"name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": null}, {"label": "reference images", "name": "images", "type": "IMAGE", "link": null}], "outputs": [{"name": "STRING", "type": "STRING", "links": null}], "title": "Prompt Enhance", "properties": {"proxyWidgets": [["-1", "prompt"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": [""]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "24d8bbfd-39d4-4774-bff0-3de40cc7a471", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 15, "lastLinkId": 14, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Prompt Enhance", "inputNode": {"id": -10, "bounding": [-2170, 2110, 138.876953125, 80]}, "outputNode": {"id": -20, "bounding": [-640, 2110, 120, 60]}, "inputs": [{"id": "aeab7216-00e0-4528-a09b-bba50845c5a6", "name": "prompt", "type": "STRING", "linkIds": [11], "pos": [-2051.123046875, 2130]}, {"id": "7b73fd36-aa31-4771-9066-f6c83879994b", "name": "images", "type": "IMAGE", "linkIds": [14], "label": "reference images", "pos": [-2051.123046875, 2150]}], "outputs": [{"id": "c7b0d930-68a1-48d1-b496-0519e5837064", "name": "STRING", "type": "STRING", "linkIds": [13], "pos": [-620, 2130]}], "widgets": [], "nodes": [{"id": 11, "type": "GeminiNode", "pos": [-1560, 1990], "size": [470, 470], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "shape": 7, "type": "IMAGE", "link": 14}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": null}, {"localized_name": "video", "name": "video", "shape": 7, "type": "VIDEO", "link": null}, {"localized_name": "files", "name": "files", "shape": 7, "type": "GEMINI_INPUT_FILES", "link": null}, {"localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": {"name": "prompt"}, "link": 11}, {"localized_name": "model", "name": "model", "type": "COMBO", "widget": {"name": "model"}, "link": null}, {"localized_name": "seed", "name": "seed", "type": "INT", "widget": {"name": "seed"}, "link": null}, {"localized_name": "system_prompt", "name": "system_prompt", "shape": 7, "type": "STRING", "widget": {"name": "system_prompt"}, "link": null}], "outputs": [{"localized_name": "STRING", "name": "STRING", "type": "STRING", "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.14.1", "Node name for S&R": "GeminiNode"}, "widgets_values": ["", "gemini-3-pro-preview", 42, "randomize", "You are an expert in prompt writing.\nBased on the input, rewrite the user's input into a detailed prompt.\nincluding camera settings, lighting, composition, and style.\nReturn the prompt only"], "color": "#432", "bgcolor": "#653"}], "groups": [], "links": [{"id": 11, "origin_id": -10, "origin_slot": 0, "target_id": 11, "target_slot": 4, "type": "STRING"}, {"id": 13, "origin_id": 11, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "STRING"}, {"id": 14, "origin_id": -10, "origin_slot": 1, "target_id": 11, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Text generation/Prompt enhance"}]}, "extra": {}}
{
"revision": 0,
"last_node_id": 15,
"last_link_id": 0,
"nodes": [
{
"id": 15,
"type": "24d8bbfd-39d4-4774-bff0-3de40cc7a471",
"pos": [
-1490,
2040
],
"size": [
400,
260
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"name": "prompt",
"type": "STRING",
"widget": {
"name": "prompt"
},
"link": null
},
{
"label": "reference images",
"name": "images",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": null
}
],
"title": "Prompt Enhance",
"properties": {
"proxyWidgets": [
[
"-1",
"prompt"
]
],
"cnr_id": "comfy-core",
"ver": "0.14.1"
},
"widgets_values": [
""
]
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "24d8bbfd-39d4-4774-bff0-3de40cc7a471",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 15,
"lastLinkId": 14,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Prompt Enhance",
"inputNode": {
"id": -10,
"bounding": [
-2170,
2110,
138.876953125,
80
]
},
"outputNode": {
"id": -20,
"bounding": [
-640,
2110,
120,
60
]
},
"inputs": [
{
"id": "aeab7216-00e0-4528-a09b-bba50845c5a6",
"name": "prompt",
"type": "STRING",
"linkIds": [
11
],
"pos": [
-2051.123046875,
2130
]
},
{
"id": "7b73fd36-aa31-4771-9066-f6c83879994b",
"name": "images",
"type": "IMAGE",
"linkIds": [
14
],
"label": "reference images",
"pos": [
-2051.123046875,
2150
]
}
],
"outputs": [
{
"id": "c7b0d930-68a1-48d1-b496-0519e5837064",
"name": "STRING",
"type": "STRING",
"linkIds": [
13
],
"pos": [
-620,
2130
]
}
],
"widgets": [],
"nodes": [
{
"id": 11,
"type": "GeminiNode",
"pos": [
-1560,
1990
],
"size": [
470,
470
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "images",
"name": "images",
"shape": 7,
"type": "IMAGE",
"link": 14
},
{
"localized_name": "audio",
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": null
},
{
"localized_name": "video",
"name": "video",
"shape": 7,
"type": "VIDEO",
"link": null
},
{
"localized_name": "files",
"name": "files",
"shape": 7,
"type": "GEMINI_INPUT_FILES",
"link": null
},
{
"localized_name": "prompt",
"name": "prompt",
"type": "STRING",
"widget": {
"name": "prompt"
},
"link": 11
},
{
"localized_name": "model",
"name": "model",
"type": "COMBO",
"widget": {
"name": "model"
},
"link": null
},
{
"localized_name": "seed",
"name": "seed",
"type": "INT",
"widget": {
"name": "seed"
},
"link": null
},
{
"localized_name": "system_prompt",
"name": "system_prompt",
"shape": 7,
"type": "STRING",
"widget": {
"name": "system_prompt"
},
"link": null
}
],
"outputs": [
{
"localized_name": "STRING",
"name": "STRING",
"type": "STRING",
"links": [
13
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.14.1",
"Node name for S&R": "GeminiNode"
},
"widgets_values": [
"",
"gemini-3-pro-preview",
42,
"randomize",
"You are an expert in prompt writing.\nBased on the input, rewrite the user's input into a detailed prompt.\nincluding camera settings, lighting, composition, and style.\nReturn the prompt only"
],
"color": "#432",
"bgcolor": "#653"
}
],
"groups": [],
"links": [
{
"id": 11,
"origin_id": -10,
"origin_slot": 0,
"target_id": 11,
"target_slot": 4,
"type": "STRING"
},
{
"id": 13,
"origin_id": 11,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "STRING"
},
{
"id": 14,
"origin_id": -10,
"origin_slot": 1,
"target_id": 11,
"target_slot": 0,
"type": "IMAGE"
}
],
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Text generation/Prompt enhance"
}
]
},
"extra": {}
}

View File

@@ -1 +1,309 @@
{"revision": 0, "last_node_id": 25, "last_link_id": 0, "nodes": [{"id": 25, "type": "621ba4e2-22a8-482d-a369-023753198b7b", "pos": [4610, -790], "size": [230, 58], "flags": {}, "order": 4, "mode": 0, "inputs": [{"label": "image", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": null}], "outputs": [{"label": "IMAGE", "localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": []}], "title": "Sharpen", "properties": {"proxyWidgets": [["24", "value"]]}, "widgets_values": []}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "621ba4e2-22a8-482d-a369-023753198b7b", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 24, "lastLinkId": 36, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Sharpen", "inputNode": {"id": -10, "bounding": [4090, -825, 120, 60]}, "outputNode": {"id": -20, "bounding": [5150, -825, 120, 60]}, "inputs": [{"id": "37011fb7-14b7-4e0e-b1a0-6a02e8da1fd7", "name": "images.image0", "type": "IMAGE", "linkIds": [34], "localized_name": "images.image0", "label": "image", "pos": [4190, -805]}], "outputs": [{"id": "e9182b3f-635c-4cd4-a152-4b4be17ae4b9", "name": "IMAGE0", "type": "IMAGE", "linkIds": [35], "localized_name": "IMAGE0", "label": "IMAGE", "pos": [5170, -805]}], "widgets": [], "nodes": [{"id": 24, "type": "PrimitiveFloat", "pos": [4280, -1240], "size": [270, 58], "flags": {}, "order": 0, "mode": 0, "inputs": [{"label": "strength", "localized_name": "value", "name": "value", "type": "FLOAT", "widget": {"name": "value"}, "link": null}], "outputs": [{"localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT", "links": [36]}], "properties": {"Node name for S&R": "PrimitiveFloat", "min": 0, "max": 3, "precision": 2, "step": 0.05}, "widgets_values": [0.5]}, {"id": 23, "type": "GLSLShader", "pos": [4570, -1240], "size": [370, 192], "flags": {}, "order": 1, "mode": 0, "inputs": [{"label": "image0", "localized_name": "images.image0", "name": "images.image0", "type": "IMAGE", "link": 34}, {"label": "image1", "localized_name": "images.image1", "name": "images.image1", "shape": 7, "type": "IMAGE", "link": null}, {"label": "u_float0", "localized_name": "floats.u_float0", "name": "floats.u_float0", "shape": 7, "type": "FLOAT", "link": 36}, {"label": "u_float1", "localized_name": "floats.u_float1", "name": "floats.u_float1", "shape": 7, "type": "FLOAT", "link": null}, {"label": "u_int0", "localized_name": "ints.u_int0", "name": "ints.u_int0", "shape": 7, "type": "INT", "link": null}, {"localized_name": "fragment_shader", "name": "fragment_shader", "type": "STRING", "widget": {"name": "fragment_shader"}, "link": null}, {"localized_name": "size_mode", "name": "size_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": {"name": "size_mode"}, "link": null}], "outputs": [{"localized_name": "IMAGE0", "name": "IMAGE0", "type": "IMAGE", "links": [35]}, {"localized_name": "IMAGE1", "name": "IMAGE1", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE2", "name": "IMAGE2", "type": "IMAGE", "links": null}, {"localized_name": "IMAGE3", "name": "IMAGE3", "type": "IMAGE", "links": null}], "properties": {"Node name for S&R": "GLSLShader"}, "widgets_values": ["#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // strength [0.0 2.0] typical: 0.31.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}", "from_input"]}], "groups": [], "links": [{"id": 36, "origin_id": 24, "origin_slot": 0, "target_id": 23, "target_slot": 2, "type": "FLOAT"}, {"id": 34, "origin_id": -10, "origin_slot": 0, "target_id": 23, "target_slot": 0, "type": "IMAGE"}, {"id": 35, "origin_id": 23, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "IMAGE"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Image Tools/Sharpen"}]}}
{
"revision": 0,
"last_node_id": 25,
"last_link_id": 0,
"nodes": [
{
"id": 25,
"type": "621ba4e2-22a8-482d-a369-023753198b7b",
"pos": [
4610,
-790
],
"size": [
230,
58
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"label": "image",
"localized_name": "images.image0",
"name": "images.image0",
"type": "IMAGE",
"link": null
}
],
"outputs": [
{
"label": "IMAGE",
"localized_name": "IMAGE0",
"name": "IMAGE0",
"type": "IMAGE",
"links": []
}
],
"title": "Sharpen",
"properties": {
"proxyWidgets": [
[
"24",
"value"
]
]
},
"widgets_values": []
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "621ba4e2-22a8-482d-a369-023753198b7b",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 24,
"lastLinkId": 36,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Sharpen",
"inputNode": {
"id": -10,
"bounding": [
4090,
-825,
120,
60
]
},
"outputNode": {
"id": -20,
"bounding": [
5150,
-825,
120,
60
]
},
"inputs": [
{
"id": "37011fb7-14b7-4e0e-b1a0-6a02e8da1fd7",
"name": "images.image0",
"type": "IMAGE",
"linkIds": [
34
],
"localized_name": "images.image0",
"label": "image",
"pos": [
4190,
-805
]
}
],
"outputs": [
{
"id": "e9182b3f-635c-4cd4-a152-4b4be17ae4b9",
"name": "IMAGE0",
"type": "IMAGE",
"linkIds": [
35
],
"localized_name": "IMAGE0",
"label": "IMAGE",
"pos": [
5170,
-805
]
}
],
"widgets": [],
"nodes": [
{
"id": 24,
"type": "PrimitiveFloat",
"pos": [
4280,
-1240
],
"size": [
270,
58
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"label": "strength",
"localized_name": "value",
"name": "value",
"type": "FLOAT",
"widget": {
"name": "value"
},
"link": null
}
],
"outputs": [
{
"localized_name": "FLOAT",
"name": "FLOAT",
"type": "FLOAT",
"links": [
36
]
}
],
"properties": {
"Node name for S&R": "PrimitiveFloat",
"min": 0,
"max": 3,
"precision": 2,
"step": 0.05
},
"widgets_values": [
0.5
]
},
{
"id": 23,
"type": "GLSLShader",
"pos": [
4570,
-1240
],
"size": [
370,
192
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"label": "image0",
"localized_name": "images.image0",
"name": "images.image0",
"type": "IMAGE",
"link": 34
},
{
"label": "image1",
"localized_name": "images.image1",
"name": "images.image1",
"shape": 7,
"type": "IMAGE",
"link": null
},
{
"label": "u_float0",
"localized_name": "floats.u_float0",
"name": "floats.u_float0",
"shape": 7,
"type": "FLOAT",
"link": 36
},
{
"label": "u_float1",
"localized_name": "floats.u_float1",
"name": "floats.u_float1",
"shape": 7,
"type": "FLOAT",
"link": null
},
{
"label": "u_int0",
"localized_name": "ints.u_int0",
"name": "ints.u_int0",
"shape": 7,
"type": "INT",
"link": null
},
{
"localized_name": "fragment_shader",
"name": "fragment_shader",
"type": "STRING",
"widget": {
"name": "fragment_shader"
},
"link": null
},
{
"localized_name": "size_mode",
"name": "size_mode",
"type": "COMFY_DYNAMICCOMBO_V3",
"widget": {
"name": "size_mode"
},
"link": null
}
],
"outputs": [
{
"localized_name": "IMAGE0",
"name": "IMAGE0",
"type": "IMAGE",
"links": [
35
]
},
{
"localized_name": "IMAGE1",
"name": "IMAGE1",
"type": "IMAGE",
"links": null
},
{
"localized_name": "IMAGE2",
"name": "IMAGE2",
"type": "IMAGE",
"links": null
},
{
"localized_name": "IMAGE3",
"name": "IMAGE3",
"type": "IMAGE",
"links": null
}
],
"properties": {
"Node name for S&R": "GLSLShader"
},
"widgets_values": [
"#version 300 es\nprecision highp float;\n\nuniform sampler2D u_image0;\nuniform vec2 u_resolution;\nuniform float u_float0; // strength [0.0 2.0] typical: 0.31.0\n\nin vec2 v_texCoord;\nlayout(location = 0) out vec4 fragColor0;\n\nvoid main() {\n vec2 texel = 1.0 / u_resolution;\n \n // Sample center and neighbors\n vec4 center = texture(u_image0, v_texCoord);\n vec4 top = texture(u_image0, v_texCoord + vec2( 0.0, -texel.y));\n vec4 bottom = texture(u_image0, v_texCoord + vec2( 0.0, texel.y));\n vec4 left = texture(u_image0, v_texCoord + vec2(-texel.x, 0.0));\n vec4 right = texture(u_image0, v_texCoord + vec2( texel.x, 0.0));\n \n // Edge enhancement (Laplacian)\n vec4 edges = center * 4.0 - top - bottom - left - right;\n \n // Add edges back scaled by strength\n vec4 sharpened = center + edges * u_float0;\n \n fragColor0 = vec4(clamp(sharpened.rgb, 0.0, 1.0), center.a);\n}",
"from_input"
]
}
],
"groups": [],
"links": [
{
"id": 36,
"origin_id": 24,
"origin_slot": 0,
"target_id": 23,
"target_slot": 2,
"type": "FLOAT"
},
{
"id": 34,
"origin_id": -10,
"origin_slot": 0,
"target_id": 23,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 35,
"origin_id": 23,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "IMAGE"
}
],
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Image Tools/Sharpen"
}
]
}
}

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long

View File

@@ -1 +1,420 @@
{"revision": 0, "last_node_id": 13, "last_link_id": 0, "nodes": [{"id": 13, "type": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", "pos": [1120, 330], "size": [240, 58], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": null}, {"name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": null}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": []}], "title": "Video Upscale(GAN x4)", "properties": {"proxyWidgets": [["-1", "model_name"]], "cnr_id": "comfy-core", "ver": "0.14.1"}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}], "links": [], "version": 0.4, "definitions": {"subgraphs": [{"id": "cf95b747-3e17-46cb-8097-cac60ff9b2e1", "version": 1, "state": {"lastGroupId": 0, "lastNodeId": 13, "lastLinkId": 19, "lastRerouteId": 0}, "revision": 0, "config": {}, "name": "Video Upscale(GAN x4)", "inputNode": {"id": -10, "bounding": [550, 460, 120, 80]}, "outputNode": {"id": -20, "bounding": [1490, 460, 120, 60]}, "inputs": [{"id": "666d633e-93e7-42dc-8d11-2b7b99b0f2a6", "name": "video", "type": "VIDEO", "linkIds": [10], "localized_name": "video", "pos": [650, 480]}, {"id": "2e23a087-caa8-4d65-99e6-662761aa905a", "name": "model_name", "type": "COMBO", "linkIds": [19], "pos": [650, 500]}], "outputs": [{"id": "0c1768ea-3ec2-412f-9af6-8e0fa36dae70", "name": "VIDEO", "type": "VIDEO", "linkIds": [15], "localized_name": "VIDEO", "pos": [1510, 480]}], "widgets": [], "nodes": [{"id": 2, "type": "ImageUpscaleWithModel", "pos": [1110, 450], "size": [320, 46], "flags": {}, "order": 1, "mode": 0, "inputs": [{"localized_name": "upscale_model", "name": "upscale_model", "type": "UPSCALE_MODEL", "link": 1}, {"localized_name": "image", "name": "image", "type": "IMAGE", "link": 14}], "outputs": [{"localized_name": "IMAGE", "name": "IMAGE", "type": "IMAGE", "links": [13]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "ImageUpscaleWithModel"}}, {"id": 11, "type": "CreateVideo", "pos": [1110, 550], "size": [320, 78], "flags": {}, "order": 3, "mode": 0, "inputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "link": 13}, {"localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO", "link": 16}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "widget": {"name": "fps"}, "link": 12}], "outputs": [{"localized_name": "VIDEO", "name": "VIDEO", "type": "VIDEO", "links": [15]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "CreateVideo"}, "widgets_values": [30]}, {"id": 10, "type": "GetVideoComponents", "pos": [1110, 330], "size": [320, 70], "flags": {}, "order": 2, "mode": 0, "inputs": [{"localized_name": "video", "name": "video", "type": "VIDEO", "link": 10}], "outputs": [{"localized_name": "images", "name": "images", "type": "IMAGE", "links": [14]}, {"localized_name": "audio", "name": "audio", "type": "AUDIO", "links": [16]}, {"localized_name": "fps", "name": "fps", "type": "FLOAT", "links": [12]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "GetVideoComponents"}}, {"id": 1, "type": "UpscaleModelLoader", "pos": [750, 450], "size": [280, 60], "flags": {}, "order": 0, "mode": 0, "inputs": [{"localized_name": "model_name", "name": "model_name", "type": "COMBO", "widget": {"name": "model_name"}, "link": 19}], "outputs": [{"localized_name": "UPSCALE_MODEL", "name": "UPSCALE_MODEL", "type": "UPSCALE_MODEL", "links": [1]}], "properties": {"cnr_id": "comfy-core", "ver": "0.10.0", "Node name for S&R": "UpscaleModelLoader", "models": [{"name": "RealESRGAN_x4plus.safetensors", "url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors", "directory": "upscale_models"}]}, "widgets_values": ["RealESRGAN_x4plus.safetensors"]}], "groups": [], "links": [{"id": 1, "origin_id": 1, "origin_slot": 0, "target_id": 2, "target_slot": 0, "type": "UPSCALE_MODEL"}, {"id": 14, "origin_id": 10, "origin_slot": 0, "target_id": 2, "target_slot": 1, "type": "IMAGE"}, {"id": 13, "origin_id": 2, "origin_slot": 0, "target_id": 11, "target_slot": 0, "type": "IMAGE"}, {"id": 16, "origin_id": 10, "origin_slot": 1, "target_id": 11, "target_slot": 1, "type": "AUDIO"}, {"id": 12, "origin_id": 10, "origin_slot": 2, "target_id": 11, "target_slot": 2, "type": "FLOAT"}, {"id": 10, "origin_id": -10, "origin_slot": 0, "target_id": 10, "target_slot": 0, "type": "VIDEO"}, {"id": 15, "origin_id": 11, "origin_slot": 0, "target_id": -20, "target_slot": 0, "type": "VIDEO"}, {"id": 19, "origin_id": -10, "origin_slot": 1, "target_id": 1, "target_slot": 0, "type": "COMBO"}], "extra": {"workflowRendererVersion": "LG"}, "category": "Video generation and editing/Enhance video"}]}, "extra": {}}
{
"revision": 0,
"last_node_id": 13,
"last_link_id": 0,
"nodes": [
{
"id": 13,
"type": "cf95b747-3e17-46cb-8097-cac60ff9b2e1",
"pos": [
1120,
330
],
"size": [
240,
58
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": null
},
{
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
},
"link": null
}
],
"outputs": [
{
"localized_name": "VIDEO",
"name": "VIDEO",
"type": "VIDEO",
"links": []
}
],
"title": "Video Upscale(GAN x4)",
"properties": {
"proxyWidgets": [
[
"-1",
"model_name"
]
],
"cnr_id": "comfy-core",
"ver": "0.14.1"
},
"widgets_values": [
"RealESRGAN_x4plus.safetensors"
]
}
],
"links": [],
"version": 0.4,
"definitions": {
"subgraphs": [
{
"id": "cf95b747-3e17-46cb-8097-cac60ff9b2e1",
"version": 1,
"state": {
"lastGroupId": 0,
"lastNodeId": 13,
"lastLinkId": 19,
"lastRerouteId": 0
},
"revision": 0,
"config": {},
"name": "Video Upscale(GAN x4)",
"inputNode": {
"id": -10,
"bounding": [
550,
460,
120,
80
]
},
"outputNode": {
"id": -20,
"bounding": [
1490,
460,
120,
60
]
},
"inputs": [
{
"id": "666d633e-93e7-42dc-8d11-2b7b99b0f2a6",
"name": "video",
"type": "VIDEO",
"linkIds": [
10
],
"localized_name": "video",
"pos": [
650,
480
]
},
{
"id": "2e23a087-caa8-4d65-99e6-662761aa905a",
"name": "model_name",
"type": "COMBO",
"linkIds": [
19
],
"pos": [
650,
500
]
}
],
"outputs": [
{
"id": "0c1768ea-3ec2-412f-9af6-8e0fa36dae70",
"name": "VIDEO",
"type": "VIDEO",
"linkIds": [
15
],
"localized_name": "VIDEO",
"pos": [
1510,
480
]
}
],
"widgets": [],
"nodes": [
{
"id": 2,
"type": "ImageUpscaleWithModel",
"pos": [
1110,
450
],
"size": [
320,
46
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"localized_name": "upscale_model",
"name": "upscale_model",
"type": "UPSCALE_MODEL",
"link": 1
},
{
"localized_name": "image",
"name": "image",
"type": "IMAGE",
"link": 14
}
],
"outputs": [
{
"localized_name": "IMAGE",
"name": "IMAGE",
"type": "IMAGE",
"links": [
13
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.10.0",
"Node name for S&R": "ImageUpscaleWithModel"
}
},
{
"id": 11,
"type": "CreateVideo",
"pos": [
1110,
550
],
"size": [
320,
78
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"link": 13
},
{
"localized_name": "audio",
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 16
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"widget": {
"name": "fps"
},
"link": 12
}
],
"outputs": [
{
"localized_name": "VIDEO",
"name": "VIDEO",
"type": "VIDEO",
"links": [
15
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.10.0",
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
30
]
},
{
"id": 10,
"type": "GetVideoComponents",
"pos": [
1110,
330
],
"size": [
320,
70
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"localized_name": "video",
"name": "video",
"type": "VIDEO",
"link": 10
}
],
"outputs": [
{
"localized_name": "images",
"name": "images",
"type": "IMAGE",
"links": [
14
]
},
{
"localized_name": "audio",
"name": "audio",
"type": "AUDIO",
"links": [
16
]
},
{
"localized_name": "fps",
"name": "fps",
"type": "FLOAT",
"links": [
12
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.10.0",
"Node name for S&R": "GetVideoComponents"
}
},
{
"id": 1,
"type": "UpscaleModelLoader",
"pos": [
750,
450
],
"size": [
280,
60
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [
{
"localized_name": "model_name",
"name": "model_name",
"type": "COMBO",
"widget": {
"name": "model_name"
},
"link": 19
}
],
"outputs": [
{
"localized_name": "UPSCALE_MODEL",
"name": "UPSCALE_MODEL",
"type": "UPSCALE_MODEL",
"links": [
1
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.10.0",
"Node name for S&R": "UpscaleModelLoader",
"models": [
{
"name": "RealESRGAN_x4plus.safetensors",
"url": "https://huggingface.co/Comfy-Org/Real-ESRGAN_repackaged/resolve/main/RealESRGAN_x4plus.safetensors",
"directory": "upscale_models"
}
]
},
"widgets_values": [
"RealESRGAN_x4plus.safetensors"
]
}
],
"groups": [],
"links": [
{
"id": 1,
"origin_id": 1,
"origin_slot": 0,
"target_id": 2,
"target_slot": 0,
"type": "UPSCALE_MODEL"
},
{
"id": 14,
"origin_id": 10,
"origin_slot": 0,
"target_id": 2,
"target_slot": 1,
"type": "IMAGE"
},
{
"id": 13,
"origin_id": 2,
"origin_slot": 0,
"target_id": 11,
"target_slot": 0,
"type": "IMAGE"
},
{
"id": 16,
"origin_id": 10,
"origin_slot": 1,
"target_id": 11,
"target_slot": 1,
"type": "AUDIO"
},
{
"id": 12,
"origin_id": 10,
"origin_slot": 2,
"target_id": 11,
"target_slot": 2,
"type": "FLOAT"
},
{
"id": 10,
"origin_id": -10,
"origin_slot": 0,
"target_id": 10,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 15,
"origin_id": 11,
"origin_slot": 0,
"target_id": -20,
"target_slot": 0,
"type": "VIDEO"
},
{
"id": 19,
"origin_id": -10,
"origin_slot": 1,
"target_id": 1,
"target_slot": 0,
"type": "COMBO"
}
],
"extra": {
"workflowRendererVersion": "LG"
},
"category": "Video generation and editing/Enhance video"
}
]
},
"extra": {}
}

View File

@@ -611,6 +611,7 @@ class AceStepDiTModel(nn.Module):
intermediate_size,
patch_size,
audio_acoustic_hidden_dim,
condition_dim=None,
layer_types=None,
sliding_window=128,
rms_norm_eps=1e-6,
@@ -640,7 +641,7 @@ class AceStepDiTModel(nn.Module):
self.time_embed = TimestepEmbedding(256, hidden_size, dtype=dtype, device=device, operations=operations)
self.time_embed_r = TimestepEmbedding(256, hidden_size, dtype=dtype, device=device, operations=operations)
self.condition_embedder = Linear(hidden_size, hidden_size, dtype=dtype, device=device)
self.condition_embedder = Linear(condition_dim, hidden_size, dtype=dtype, device=device)
if layer_types is None:
layer_types = ["full_attention"] * num_layers
@@ -1035,6 +1036,9 @@ class AceStepConditionGenerationModel(nn.Module):
fsq_dim=2048,
fsq_levels=[8, 8, 8, 5, 5, 5],
fsq_input_num_quantizers=1,
encoder_hidden_size=2048,
encoder_intermediate_size=6144,
encoder_num_heads=16,
audio_model=None,
dtype=None,
device=None,
@@ -1054,24 +1058,24 @@ class AceStepConditionGenerationModel(nn.Module):
self.decoder = AceStepDiTModel(
in_channels, hidden_size, num_dit_layers, num_heads, num_kv_heads, head_dim,
intermediate_size, patch_size, audio_acoustic_hidden_dim,
intermediate_size, patch_size, audio_acoustic_hidden_dim, condition_dim=encoder_hidden_size,
layer_types=layer_types, sliding_window=sliding_window, rms_norm_eps=rms_norm_eps,
dtype=dtype, device=device, operations=operations
)
self.encoder = AceStepConditionEncoder(
text_hidden_dim, timbre_hidden_dim, hidden_size, num_lyric_layers, num_timbre_layers,
num_heads, num_kv_heads, head_dim, intermediate_size, rms_norm_eps,
text_hidden_dim, timbre_hidden_dim, encoder_hidden_size, num_lyric_layers, num_timbre_layers,
encoder_num_heads, num_kv_heads, head_dim, encoder_intermediate_size, rms_norm_eps,
dtype=dtype, device=device, operations=operations
)
self.tokenizer = AceStepAudioTokenizer(
audio_acoustic_hidden_dim, hidden_size, pool_window_size, fsq_dim=fsq_dim, fsq_levels=fsq_levels, fsq_input_num_quantizers=fsq_input_num_quantizers, num_layers=num_tokenizer_layers, head_dim=head_dim, rms_norm_eps=rms_norm_eps,
audio_acoustic_hidden_dim, encoder_hidden_size, pool_window_size, fsq_dim=fsq_dim, fsq_levels=fsq_levels, fsq_input_num_quantizers=fsq_input_num_quantizers, num_layers=num_tokenizer_layers, head_dim=head_dim, rms_norm_eps=rms_norm_eps,
dtype=dtype, device=device, operations=operations
)
self.detokenizer = AudioTokenDetokenizer(
hidden_size, pool_window_size, audio_acoustic_hidden_dim, num_layers=2, head_dim=head_dim,
encoder_hidden_size, pool_window_size, audio_acoustic_hidden_dim, num_layers=2, head_dim=head_dim,
dtype=dtype, device=device, operations=operations
)
self.null_condition_emb = nn.Parameter(torch.empty(1, 1, hidden_size, dtype=dtype, device=device))
self.null_condition_emb = nn.Parameter(torch.empty(1, 1, encoder_hidden_size, dtype=dtype, device=device))
def prepare_condition(
self,

View File

@@ -155,6 +155,7 @@ class AutoencodingEngineLegacy(AutoencodingEngine):
def __init__(self, embed_dim: int, **kwargs):
self.max_batch_size = kwargs.pop("max_batch_size", None)
ddconfig = kwargs.pop("ddconfig")
decoder_ddconfig = kwargs.pop("decoder_ddconfig", ddconfig)
super().__init__(
encoder_config={
"target": "comfy.ldm.modules.diffusionmodules.model.Encoder",
@@ -162,7 +163,7 @@ class AutoencodingEngineLegacy(AutoencodingEngine):
},
decoder_config={
"target": "comfy.ldm.modules.diffusionmodules.model.Decoder",
"params": ddconfig,
"params": decoder_ddconfig,
},
**kwargs,
)

View File

@@ -696,6 +696,15 @@ def detect_unet_config(state_dict, key_prefix, metadata=None):
if '{}encoder.lyric_encoder.layers.0.input_layernorm.weight'.format(key_prefix) in state_dict_keys:
dit_config = {}
dit_config["audio_model"] = "ace1.5"
head_dim = 128
dit_config["hidden_size"] = state_dict['{}decoder.layers.0.self_attn_norm.weight'.format(key_prefix)].shape[0]
dit_config["intermediate_size"] = state_dict['{}decoder.layers.0.mlp.gate_proj.weight'.format(key_prefix)].shape[0]
dit_config["num_heads"] = state_dict['{}decoder.layers.0.self_attn.q_proj.weight'.format(key_prefix)].shape[0] // head_dim
dit_config["encoder_hidden_size"] = state_dict['{}encoder.lyric_encoder.layers.0.input_layernorm.weight'.format(key_prefix)].shape[0]
dit_config["encoder_num_heads"] = state_dict['{}encoder.lyric_encoder.layers.0.self_attn.q_proj.weight'.format(key_prefix)].shape[0] // head_dim
dit_config["encoder_intermediate_size"] = state_dict['{}encoder.lyric_encoder.layers.0.mlp.gate_proj.weight'.format(key_prefix)].shape[0]
dit_config["num_dit_layers"] = count_blocks(state_dict_keys, '{}decoder.layers.'.format(key_prefix) + '{}.')
return dit_config
if '{}encoder.pan_blocks.1.cv4.conv.weight'.format(key_prefix) in state_dict_keys: # RT-DETR_v4

View File

@@ -556,12 +556,19 @@ class VAE:
old_memory_used_decode = self.memory_used_decode
self.memory_used_decode = lambda shape, dtype: old_memory_used_decode(shape, dtype) * 4.0
decoder_ch = sd['decoder.conv_in.weight'].shape[0] // ddconfig['ch_mult'][-1]
if decoder_ch != ddconfig['ch']:
decoder_ddconfig = ddconfig.copy()
decoder_ddconfig['ch'] = decoder_ch
else:
decoder_ddconfig = None
if 'post_quant_conv.weight' in sd:
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1])
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1], **({"decoder_ddconfig": decoder_ddconfig} if decoder_ddconfig is not None else {}))
else:
self.first_stage_model = AutoencodingEngine(regularizer_config={'target': "comfy.ldm.models.autoencoder.DiagonalGaussianRegularizer"},
encoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Encoder", 'params': ddconfig},
decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': ddconfig})
decoder_config={'target': "comfy.ldm.modules.diffusionmodules.model.Decoder", 'params': decoder_ddconfig if decoder_ddconfig is not None else ddconfig})
elif "decoder.layers.1.layers.0.beta" in sd:
config = {}
param_key = None

View File

@@ -9,6 +9,7 @@ from comfy_api.latest._input import (
CurveInput,
MonotoneCubicCurve,
LinearCurve,
RangeInput,
)
__all__ = [
@@ -21,4 +22,5 @@ __all__ = [
"CurveInput",
"MonotoneCubicCurve",
"LinearCurve",
"RangeInput",
]

View File

@@ -1,5 +1,6 @@
from .basic_types import ImageInput, AudioInput, MaskInput, LatentInput
from .curve_types import CurvePoint, CurveInput, MonotoneCubicCurve, LinearCurve
from .range_types import RangeInput
from .video_types import VideoInput
__all__ = [
@@ -12,4 +13,5 @@ __all__ = [
"CurveInput",
"MonotoneCubicCurve",
"LinearCurve",
"RangeInput",
]

View File

@@ -0,0 +1,70 @@
from __future__ import annotations
import logging
import math
import numpy as np
logger = logging.getLogger(__name__)
class RangeInput:
"""Represents a levels/range adjustment: input range [min, max] with
optional midpoint (gamma control).
Generates a 1D LUT identical to GIMP's levels mapping:
1. Normalize input to [0, 1] using [min, max]
2. Apply gamma correction: pow(value, 1/gamma)
3. Clamp to [0, 1]
The midpoint field is a position in [0, 1] representing where the
midtone falls within [min, max]. It maps to gamma via:
gamma = -log2(midpoint)
So midpoint=0.5 → gamma=1.0 (linear).
"""
def __init__(self, min_val: float, max_val: float, midpoint: float | None = None):
self.min_val = min_val
self.max_val = max_val
self.midpoint = midpoint
@staticmethod
def from_raw(data) -> RangeInput:
if isinstance(data, RangeInput):
return data
if isinstance(data, dict):
return RangeInput(
min_val=float(data.get("min", 0.0)),
max_val=float(data.get("max", 1.0)),
midpoint=float(data["midpoint"]) if data.get("midpoint") is not None else None,
)
raise TypeError(f"Cannot convert {type(data)} to RangeInput")
def to_lut(self, size: int = 256) -> np.ndarray:
"""Generate a float64 lookup table mapping [0, 1] input through this
levels adjustment.
The LUT maps normalized input values (0..1) to output values (0..1),
matching the GIMP levels formula.
"""
xs = np.linspace(0.0, 1.0, size, dtype=np.float64)
in_range = self.max_val - self.min_val
if abs(in_range) < 1e-10:
return np.where(xs >= self.min_val, 1.0, 0.0).astype(np.float64)
# Normalize: map [min, max] → [0, 1]
result = (xs - self.min_val) / in_range
result = np.clip(result, 0.0, 1.0)
# Gamma correction from midpoint
if self.midpoint is not None and self.midpoint > 0 and self.midpoint != 0.5:
gamma = max(-math.log2(self.midpoint), 0.001)
inv_gamma = 1.0 / gamma
mask = result > 0
result[mask] = np.power(result[mask], inv_gamma)
return result
def __repr__(self) -> str:
mid = f", midpoint={self.midpoint}" if self.midpoint is not None else ""
return f"RangeInput(min={self.min_val}, max={self.max_val}{mid})"

View File

@@ -1266,6 +1266,43 @@ class Histogram(ComfyTypeIO):
Type = list[int]
@comfytype(io_type="RANGE")
class Range(ComfyTypeIO):
from comfy_api.input import RangeInput
if TYPE_CHECKING:
Type = RangeInput
class Input(WidgetInput):
def __init__(self, id: str, display_name: str=None, optional=False, tooltip: str=None,
socketless: bool=True, default: dict=None,
display: str=None,
gradient_stops: list=None,
show_midpoint: bool=None,
midpoint_scale: str=None,
value_min: float=None,
value_max: float=None,
advanced: bool=None):
super().__init__(id, display_name, optional, tooltip, None, default, socketless, None, None, None, None, advanced)
if default is None:
self.default = {"min": 0.0, "max": 1.0}
self.display = display
self.gradient_stops = gradient_stops
self.show_midpoint = show_midpoint
self.midpoint_scale = midpoint_scale
self.value_min = value_min
self.value_max = value_max
def as_dict(self):
return super().as_dict() | prune_dict({
"display": self.display,
"gradient_stops": self.gradient_stops,
"show_midpoint": self.show_midpoint,
"midpoint_scale": self.midpoint_scale,
"value_min": self.value_min,
"value_max": self.value_max,
})
DYNAMIC_INPUT_LOOKUP: dict[str, Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]] = {}
def register_dynamic_input_func(io_type: str, func: Callable[[dict[str, Any], dict[str, Any], tuple[str, dict[str, Any]], str, list[str] | None], None]):
DYNAMIC_INPUT_LOOKUP[io_type] = func
@@ -2276,5 +2313,6 @@ __all__ = [
"BoundingBox",
"Curve",
"Histogram",
"Range",
"NodeReplace",
]

View File

@@ -80,7 +80,7 @@ class EmptyAceStepLatentAudio(io.ComfyNode):
@classmethod
def execute(cls, seconds, batch_size) -> io.NodeOutput:
length = int(seconds * 44100 / 512 / 8)
latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device())
latent = torch.zeros([batch_size, 8, 16, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
return io.NodeOutput({"samples": latent, "type": "audio"})
@@ -103,7 +103,7 @@ class EmptyAceStep15LatentAudio(io.ComfyNode):
@classmethod
def execute(cls, seconds, batch_size) -> io.NodeOutput:
length = round((seconds * 48000 / 1920))
latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device())
latent = torch.zeros([batch_size, 64, length], device=comfy.model_management.intermediate_device(), dtype=comfy.model_management.intermediate_dtype())
return io.NodeOutput({"samples": latent, "type": "audio"})
class ReferenceAudio(io.ComfyNode):