DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-14 12:56:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: unify text encoder selection across H3 variants (#2340)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-11-13 00:23:54 +08:00
1 parent 8b1e9df27d
commit b9d7176bf8
14 files changed
+123 -57
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

examples/server/recipes/hyperflow-h3-flash-fl2va.json
+12 -2
View File
@@ -3,7 +3,7 @@
"id": "hyperflow-h3-flash-fl2va",
"name": "HyperFlow H3 Flash FL2VA",
"size_multiple": 32,
"description": "Generate video and audio from text, optionally with start/end images. Use the HyperFlow H3 Flash FL2VA transformer. Reuses MiniMax-H3 components with the HyperFlow 6-step schedule. Audio VAE is optional for silent video.",
"description": "Generate video and audio from text, optionally with start/end images. Use the HyperFlow H3 Flash FL2VA transformer. Reuses MiniMax-H3 components with either the MiniMax-H3 Qwen3-VL-32B text encoder or Qwen3-VL-4B with the P-H3 text connector and the HyperFlow 6-step schedule. Audio VAE is optional for silent video.",
"model_url": "https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash",
"slots": [
{
@@ -14,7 +14,17 @@
{
"id": "llm",
"required": true,
"label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
"label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
},
{
"id": "llm_vision",
"required": false,
"label": "Vision tower (when not included in the text encoder)"
},
{
"id": "embeddings_connectors",
"required": false,
"label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
},
{
"id": "vae",
examples/server/recipes/hyperflow-h3-flash-ref2va.json
+12 -2
View File
@@ -3,7 +3,7 @@
"id": "hyperflow-h3-flash-ref2va",
"name": "HyperFlow H3 Flash Ref2VA",
"size_multiple": 32,
"description": "Generate video and audio with reference images. Use the HyperFlow H3 Flash Ref2VA transformer; video/audio references are not validated for these weights. Reuses MiniMax-H3 components with the HyperFlow 6-step schedule. Audio VAE is optional for silent video.",
"description": "Generate video and audio with reference images. Use the HyperFlow H3 Flash Ref2VA transformer; video/audio references are not validated for these weights. Reuses MiniMax-H3 components with either the MiniMax-H3 Qwen3-VL-32B text encoder or Qwen3-VL-4B with the P-H3 text connector and the HyperFlow 6-step schedule. Reference images need the matching vision tower. Audio VAE is optional for silent video.",
"model_url": "https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash",
"slots": [
{
@@ -14,7 +14,17 @@
{
"id": "llm",
"required": true,
"label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
"label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
},
{
"id": "llm_vision",
"required": false,
"label": "Vision tower (required for reference images when not included in the text encoder)"
},
{
"id": "embeddings_connectors",
"required": false,
"label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
},
{
"id": "vae",
examples/server/recipes/minimax-h3-fl2va.json
+12 -2
View File
@@ -3,7 +3,7 @@
"id": "minimax-h3-fl2va",
"name": "MiniMax H3 FL2VA",
"size_multiple": 32,
"description": "Generate video and audio, optionally with start/end images. Supports full and pruned FL2VA weights. Audio VAE is optional for silent video.",
"description": "Generate video and audio, optionally with start/end images. Supports full and pruned FL2VA weights with either the MiniMax-H3 Qwen3-VL-32B text encoder or Qwen3-VL-4B with the P-H3 text connector. Audio VAE is optional for silent video.",
"model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3",
"slots": [
{
@@ -13,7 +13,17 @@
{
"id": "llm",
"required": true,
"label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
"label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
},
{
"id": "llm_vision",
"required": false,
"label": "Vision tower (when not included in the text encoder)"
},
{
"id": "embeddings_connectors",
"required": false,
"label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
},
{
"id": "vae",
examples/server/recipes/minimax-h3-ref2va.json
+12 -2
View File
@@ -3,7 +3,7 @@
"id": "minimax-h3-ref2va",
"name": "MiniMax H3 Ref2VA",
"size_multiple": 32,
"description": "Supply image, video or audio references with compatible Ref2VA weights. Audio VAE is optional for silent video.",
"description": "Supply image, video or audio references with compatible Ref2VA weights. Use either the MiniMax-H3 Qwen3-VL-32B text encoder or Qwen3-VL-4B with the P-H3 text connector. Image/video references need the matching vision tower. Audio VAE is optional for silent video.",
"model_url": "https://huggingface.co/MiniMaxAI/MiniMax-H3",
"slots": [
{
@@ -13,7 +13,17 @@
{
"id": "llm",
"required": true,
"label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
"label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
},
{
"id": "llm_vision",
"required": false,
"label": "Vision tower (required for image/video references when not included in the text encoder)"
},
{
"id": "embeddings_connectors",
"required": false,
"label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
},
{
"id": "vae",
examples/server/recipes/p-h3-image.json
+3 -3
View File
@@ -3,7 +3,7 @@
"id": "p-h3-image",
"name": "P-H3-Image",
"size_multiple": 32,
"description": "Supports text-to-image and reference-image editing with the fixed 8-step schedule. Use the P-H3 single-frame VAE and Qwen3-VL-4B with its vision tower. Supply the P-H3 text connector separately unless it is included in the text encoder.",
"description": "Supports text-to-image and reference-image editing with the fixed 8-step schedule. Use the P-H3 single-frame VAE and either Qwen3-VL-4B with the P-H3 text connector or the MiniMax-H3 Qwen3-VL-32B text encoder. Reference images need the matching vision tower.",
"model_url": "https://huggingface.co/PrunaAI/P-H3-Image",
"slots": [
{
@@ -13,7 +13,7 @@
{
"id": "llm",
"required": true,
"label": "Qwen 3 VL 4B Text Encoder"
"label": "MiniMax-H3 Qwen 3 VL 32B or P-H3 Qwen 3 VL 4B Text Encoder"
},
{
"id": "llm_vision",
@@ -23,7 +23,7 @@
{
"id": "embeddings_connectors",
"required": false,
"label": "P-H3 Text Connector (required when not included in the text encoder)"
"label": "P-H3 Text Connector (for Qwen 3 VL 4B, when not included in the text encoder)"
},
{
"id": "vae",