mirror of
https://github.com/leejet/stable-diffusion.cpp.git
synced 2026-11-12 03:49:09 +00:00
feat: support HyperFlow H3 Flash (#2299)
Co-authored-by: Video Rebirth <opensource@videorebirth.com>
This commit is contained in:
leejetandVideo Rebirth authored and GitHub committed
1 parent
3d315c47d4
commit
80c4707c53
9 files changed
+370
-49
No files matched your search
@@ -1540,6 +1540,12 @@ ArgOptions SDGenerationParams::get_options() {
|
||||
sigmas_str = "1.0,0.978453,0.95418,0.926626,0.89508,0.845148,0.704534,0.414568,0.0";
|
||||
} else if (sigmas_str == "p-h3-image") {
|
||||
sigmas_str = "1.0,0.984753,0.967905,0.951688,0.925372,0.881923,0.810083,0.528718,0.0";
|
||||
} else if (sigmas_str == "hyperflow-h3-flash-4") {
|
||||
sigmas_str = "1.0,0.962575853,0.755781889,0.312497854,0.0";
|
||||
} else if (sigmas_str == "hyperflow-h3-flash-6") {
|
||||
sigmas_str = "1.0,0.982655942,0.914642572,0.674755692,0.385223746,0.159055337,0.0";
|
||||
} else if (sigmas_str == "hyperflow-h3-flash-8") {
|
||||
sigmas_str = "1.0,0.993909776,0.9842875,0.966063678,0.923076928,0.834942341,0.696852028,0.468753338,0.0";
|
||||
}
|
||||
if (!sigmas_str.empty() && sigmas_str.front() == '[') {
|
||||
sigmas_str.erase(0, 1);
|
||||
@@ -1787,11 +1793,11 @@ ArgOptions SDGenerationParams::get_options() {
|
||||
on_scheduler_arg},
|
||||
{"",
|
||||
"--sigmas",
|
||||
"custom sigma values for the sampler, comma-separated (e.g., \"14.61,7.8,3.5,0.0\") or preset: qwen-image-2.1-turbo, p-h3-image.",
|
||||
"custom sigma values for the sampler, comma-separated (e.g., \"14.61,7.8,3.5,0.0\") or preset: qwen-image-2.1-turbo, p-h3-image, hyperflow-h3-flash-4, hyperflow-h3-flash-6, hyperflow-h3-flash-8.",
|
||||
on_sigmas_arg},
|
||||
{"",
|
||||
"--hires-sigmas",
|
||||
"custom sigma values for the highres fix second pass, comma-separated (e.g., \"0.85,0.725,0.421875,0.0\") or preset: qwen-image-2.1-turbo, p-h3-image.",
|
||||
"custom sigma values for the highres fix second pass, comma-separated (e.g., \"0.85,0.725,0.421875,0.0\") or preset: qwen-image-2.1-turbo, p-h3-image, hyperflow-h3-flash-4, hyperflow-h3-flash-6, hyperflow-h3-flash-8.",
|
||||
on_hires_sigmas_arg},
|
||||
{"",
|
||||
"--skip-layers",
|
||||
|
||||
@@ -42,6 +42,8 @@ For community edit adapters and other optional extensions, these are the base-mo
|
||||
| `flux3-klein` | 1 | 16 | 1024 × 1024 | [Source](https://raw.githubusercontent.com/black-forest-labs/flux-3-image-klein/main/README.md) |
|
||||
| `flux3-klein-base` | 4 | 20 | 1024 × 1024 | [Source](https://raw.githubusercontent.com/black-forest-labs/flux-3-image-klein/main/src/flux3/pipeline.py) |
|
||||
| `hidream-o1-dev` | 1 | 20 | 1024 × 1024 | [Source](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev) |
|
||||
| `hyperflow-h3-flash-fl2va` | 1 | 6 | 1344 × 768 | [Source](https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash) Two-time FL2VA checkpoint; native text and first/last-frame generation. Fixed 6-step video sigma grid with shift 12, 124 frames at 24 FPS. Reuses MiniMax-H3 components. |
|
||||
| `hyperflow-h3-flash-ref2va` | 1 | 6 | 1344 × 768 | [Source](https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash) Separate two-time Ref2VA checkpoint; image references. Same schedule and components as FL2VA; video/audio references remain unverified. |
|
||||
| `hunyuan-video-15-i2v` | 6 | 20 | 1280 × 720 | [Source](https://huggingface.co/tencent/HunyuanVideo-1.5) 720p base I2V defaults; CFG/step-distilled and 480p checkpoints use different settings. |
|
||||
| `hunyuan-video-15-t2v` | 6 | 20 | 1280 × 720 | [Source](https://huggingface.co/tencent/HunyuanVideo-1.5) 720p base T2V defaults; CFG-distilled / 480p checkpoints need their published settings. |
|
||||
| `ideogram4` | 7 | 20 | 1024 × 1024 | [Source](https://raw.githubusercontent.com/ideogram-oss/ideogram4/main/docs/inference.md) Constant-guidance pipeline defaults; this recipe does not reproduce the CLI’s per-step guidance schedule. |
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"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.",
|
||||
"model_url": "https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash",
|
||||
"slots": [
|
||||
{
|
||||
"id": "diffusion_model",
|
||||
"required": true,
|
||||
"label": "HyperFlow H3 Flash FL2VA Transformer"
|
||||
},
|
||||
{
|
||||
"id": "llm",
|
||||
"required": true,
|
||||
"label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
|
||||
},
|
||||
{
|
||||
"id": "vae",
|
||||
"required": false,
|
||||
"label": "MiniMax H3 Video VAE"
|
||||
},
|
||||
{
|
||||
"id": "tae",
|
||||
"required": false
|
||||
},
|
||||
{
|
||||
"id": "audio_vae",
|
||||
"required": false,
|
||||
"label": "MiniMax H3 Audio VAE"
|
||||
}
|
||||
],
|
||||
"required_any": [
|
||||
[
|
||||
"vae",
|
||||
"tae"
|
||||
]
|
||||
],
|
||||
"video_constraints": {
|
||||
"frame_step": 17,
|
||||
"frame_offset": 5,
|
||||
"frame_rounding": "ceil",
|
||||
"min_frames": 5,
|
||||
"fixed_fps": 24
|
||||
},
|
||||
"defaults": {
|
||||
"video_frames": 124,
|
||||
"fps": 24,
|
||||
"cfg_scale": 1,
|
||||
"width": 1344,
|
||||
"height": 768,
|
||||
"sampling_method": "euler",
|
||||
"steps": 6,
|
||||
"flow_shift": 12,
|
||||
"custom_sigmas": [
|
||||
1.0,
|
||||
0.982655942,
|
||||
0.914642572,
|
||||
0.674755692,
|
||||
0.385223746,
|
||||
0.159055337,
|
||||
0.0
|
||||
]
|
||||
},
|
||||
"features": [
|
||||
"end_image",
|
||||
"flow_shift",
|
||||
"init_image"
|
||||
],
|
||||
"disabled_features": [
|
||||
"img2img",
|
||||
"mask_image"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,74 @@
|
||||
{
|
||||
"schema_version": 1,
|
||||
"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.",
|
||||
"model_url": "https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash",
|
||||
"slots": [
|
||||
{
|
||||
"id": "diffusion_model",
|
||||
"required": true,
|
||||
"label": "HyperFlow H3 Flash REF2VA Transformer"
|
||||
},
|
||||
{
|
||||
"id": "llm",
|
||||
"required": true,
|
||||
"label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
|
||||
},
|
||||
{
|
||||
"id": "vae",
|
||||
"required": false,
|
||||
"label": "MiniMax H3 Video VAE"
|
||||
},
|
||||
{
|
||||
"id": "tae",
|
||||
"required": false
|
||||
},
|
||||
{
|
||||
"id": "audio_vae",
|
||||
"required": false,
|
||||
"label": "MiniMax H3 Audio VAE"
|
||||
}
|
||||
],
|
||||
"required_any": [
|
||||
[
|
||||
"vae",
|
||||
"tae"
|
||||
]
|
||||
],
|
||||
"video_constraints": {
|
||||
"frame_step": 17,
|
||||
"frame_offset": 5,
|
||||
"frame_rounding": "ceil",
|
||||
"min_frames": 5,
|
||||
"fixed_fps": 24
|
||||
},
|
||||
"defaults": {
|
||||
"video_frames": 124,
|
||||
"fps": 24,
|
||||
"cfg_scale": 1,
|
||||
"width": 1344,
|
||||
"height": 768,
|
||||
"sampling_method": "euler",
|
||||
"steps": 6,
|
||||
"flow_shift": 12,
|
||||
"custom_sigmas": [
|
||||
1.0,
|
||||
0.982655942,
|
||||
0.914642572,
|
||||
0.674755692,
|
||||
0.385223746,
|
||||
0.159055337,
|
||||
0.0
|
||||
]
|
||||
},
|
||||
"features": [
|
||||
"flow_shift",
|
||||
"ref_images"
|
||||
],
|
||||
"disabled_features": [
|
||||
"img2img",
|
||||
"mask_image"
|
||||
]
|
||||
}
|
||||
Reference in new issue
Block a user