refactor: define VAE tile dimensions in image pixels (#2059)

This commit is contained in:
leejet
2026-09-25 18:20:32 +08:00
committed by GitHub
parent 39ada0863b
commit 19bbbca1c7
14 changed files with 298 additions and 174 deletions
+29 -29
View File
@@ -1341,7 +1341,7 @@ ArgOptions SDGenerationParams::get_options() {
&embed_image_metadata},
{"",
"--vae-tiling",
"process vae in tiles to reduce memory usage",
"process vae encode and decode in spatial tiles to reduce memory usage (default: 256x256 image pixels)",
true,
&vae_tiling_params.enabled},
{"",
@@ -1605,12 +1605,12 @@ ArgOptions SDGenerationParams::get_options() {
size_t x_pos = tile_size_str.find('x');
try {
if (x_pos != std::string::npos) {
std::string tile_x_str = tile_size_str.substr(0, x_pos);
std::string tile_y_str = tile_size_str.substr(x_pos + 1);
vae_tiling_params.tile_size_x = std::stoi(tile_x_str);
vae_tiling_params.tile_size_y = std::stoi(tile_y_str);
std::string tile_w_str = tile_size_str.substr(0, x_pos);
std::string tile_h_str = tile_size_str.substr(x_pos + 1);
vae_tiling_params.tile_size_w = std::stoi(tile_w_str);
vae_tiling_params.tile_size_h = std::stoi(tile_h_str);
} else {
vae_tiling_params.tile_size_x = vae_tiling_params.tile_size_y = std::stoi(tile_size_str);
vae_tiling_params.tile_size_w = vae_tiling_params.tile_size_h = std::stoi(tile_size_str);
}
} catch (const std::invalid_argument&) {
return -1;
@@ -1628,12 +1628,12 @@ ArgOptions SDGenerationParams::get_options() {
size_t x_pos = rel_size_str.find('x');
try {
if (x_pos != std::string::npos) {
std::string rel_x_str = rel_size_str.substr(0, x_pos);
std::string rel_y_str = rel_size_str.substr(x_pos + 1);
vae_tiling_params.rel_size_x = std::stof(rel_x_str);
vae_tiling_params.rel_size_y = std::stof(rel_y_str);
std::string rel_w_str = rel_size_str.substr(0, x_pos);
std::string rel_h_str = rel_size_str.substr(x_pos + 1);
vae_tiling_params.rel_size_w = std::stof(rel_w_str);
vae_tiling_params.rel_size_h = std::stof(rel_h_str);
} else {
vae_tiling_params.rel_size_x = vae_tiling_params.rel_size_y = std::stof(rel_size_str);
vae_tiling_params.rel_size_w = vae_tiling_params.rel_size_h = std::stof(rel_size_str);
}
} catch (const std::invalid_argument&) {
return -1;
@@ -1763,11 +1763,11 @@ ArgOptions SDGenerationParams::get_options() {
on_scm_policy_arg},
{"",
"--vae-tile-size",
"tile size for vae tiling in latent units, not image pixels, format [X]x[Y] (default: 32x32)",
"tile size for vae encode and decode in image pixels, format [W]x[H] or [S] (default: 256x256; requires --vae-tiling)",
on_tile_size_arg},
{"",
"--vae-relative-tile-size",
"relative tile size for vae tiling, format [X]x[Y], in fraction of image size if < 1, in number of tiles per dim if >=1 (overrides --vae-tile-size)",
"relative tile size for vae encode and decode, format [W]x[H] or [S]: <=1 is a dimension fraction, >1 a target tile count (overrides --vae-tile-size; requires --vae-tiling)",
on_relative_tile_size_arg},
{"",
"--prompt-file",
@@ -2224,20 +2224,20 @@ bool SDGenerationParams::from_json_str(
if (tiling_json.contains("temporal_tiling") && tiling_json["temporal_tiling"].is_boolean()) {
vae_tiling_params.temporal_tiling = tiling_json["temporal_tiling"];
}
if (tiling_json.contains("tile_size_x") && tiling_json["tile_size_x"].is_number_integer()) {
vae_tiling_params.tile_size_x = tiling_json["tile_size_x"];
if (tiling_json.contains("tile_size_w") && tiling_json["tile_size_w"].is_number_integer()) {
vae_tiling_params.tile_size_w = tiling_json["tile_size_w"];
}
if (tiling_json.contains("tile_size_y") && tiling_json["tile_size_y"].is_number_integer()) {
vae_tiling_params.tile_size_y = tiling_json["tile_size_y"];
if (tiling_json.contains("tile_size_h") && tiling_json["tile_size_h"].is_number_integer()) {
vae_tiling_params.tile_size_h = tiling_json["tile_size_h"];
}
if (tiling_json.contains("target_overlap") && tiling_json["target_overlap"].is_number()) {
vae_tiling_params.target_overlap = tiling_json["target_overlap"];
}
if (tiling_json.contains("rel_size_x") && tiling_json["rel_size_x"].is_number()) {
vae_tiling_params.rel_size_x = tiling_json["rel_size_x"];
if (tiling_json.contains("rel_size_w") && tiling_json["rel_size_w"].is_number()) {
vae_tiling_params.rel_size_w = tiling_json["rel_size_w"];
}
if (tiling_json.contains("rel_size_y") && tiling_json["rel_size_y"].is_number()) {
vae_tiling_params.rel_size_y = tiling_json["rel_size_y"];
if (tiling_json.contains("rel_size_h") && tiling_json["rel_size_h"].is_number()) {
vae_tiling_params.rel_size_h = tiling_json["rel_size_h"];
}
if (tiling_json.contains("extra_tiling_args") && tiling_json["extra_tiling_args"].is_string()) {
extra_tiling_args = tiling_json["extra_tiling_args"].get<std::string>();
@@ -2934,11 +2934,11 @@ std::string SDGenerationParams::to_string() const {
<< " vae_tiling_params: { "
<< vae_tiling_params.enabled << ", "
<< vae_tiling_params.temporal_tiling << ", "
<< vae_tiling_params.tile_size_x << ", "
<< vae_tiling_params.tile_size_y << ", "
<< vae_tiling_params.tile_size_w << ", "
<< vae_tiling_params.tile_size_h << ", "
<< vae_tiling_params.target_overlap << ", "
<< vae_tiling_params.rel_size_x << ", "
<< vae_tiling_params.rel_size_y << ", "
<< vae_tiling_params.rel_size_w << ", "
<< vae_tiling_params.rel_size_h << ", "
<< "\"" << extra_tiling_args << "\" },\n"
<< "}";
return oss.str();
@@ -3140,11 +3140,11 @@ std::string build_sdcpp_image_metadata_json(const SDContextParams& ctx_params,
root["vae_tiling"] = {
{"enabled", gen_params.vae_tiling_params.enabled},
{"temporal_tiling", gen_params.vae_tiling_params.temporal_tiling},
{"tile_size_x", gen_params.vae_tiling_params.tile_size_x},
{"tile_size_y", gen_params.vae_tiling_params.tile_size_y},
{"tile_size_w", gen_params.vae_tiling_params.tile_size_w},
{"tile_size_h", gen_params.vae_tiling_params.tile_size_h},
{"target_overlap", gen_params.vae_tiling_params.target_overlap},
{"rel_size_x", gen_params.vae_tiling_params.rel_size_x},
{"rel_size_y", gen_params.vae_tiling_params.rel_size_y},
{"rel_size_w", gen_params.vae_tiling_params.rel_size_w},
{"rel_size_h", gen_params.vae_tiling_params.rel_size_h},
{"extra_tiling_args", gen_params.extra_tiling_args},
};
}
+22 -20
View File
@@ -524,11 +524,11 @@ Shared default fields used by both `img_gen` and `vid_gen`:
| `vae_tiling_params` | `object` |
| `vae_tiling_params.enabled` | `boolean` |
| `vae_tiling_params.temporal_tiling` | `boolean` |
| `vae_tiling_params.tile_size_x` | `integer` |
| `vae_tiling_params.tile_size_y` | `integer` |
| `vae_tiling_params.tile_size_w` | `integer` |
| `vae_tiling_params.tile_size_h` | `integer` |
| `vae_tiling_params.target_overlap` | `number` |
| `vae_tiling_params.rel_size_x` | `number` |
| `vae_tiling_params.rel_size_y` | `number` |
| `vae_tiling_params.rel_size_w` | `number` |
| `vae_tiling_params.rel_size_h` | `number` |
| `vae_tiling_params.extra_tiling_args` | `string` |
| `cache_mode` | `string` |
| `cache_option` | `string` |
@@ -537,6 +537,8 @@ Shared default fields used by both `img_gen` and `vid_gen`:
| `output_format` | `string` |
| `output_compression` | `integer` |
`vae_tiling_params.tile_size_w` and `tile_size_h` are in **image pixels**, with `0` selecting the 256-pixel default. Both encode and decode use these sizes without an encoding multiplier. Positive `rel_size_w`/`rel_size_h` values override the corresponding absolute size: values up to 1 are dimension fractions, and values greater than 1 are target tile counts. Set `enabled` to use spatial tiling. Sizes are aligned down to the VAE scale factor and capped at the input dimensions; explicit sizes below the minimum supported tile size are rejected. These fields previously used latent units; see [VAE tiling](../../docs/performance.md#use-vae-tiling-to-reduce-encode-and-decode-memory-usage) for migration and OOM retry behavior.
`vae_tiling_params.extra_tiling_args` accepts a key=value list. Supported video VAEs accept `temporal_tile_frames` (alias `temporal_tile_size`, default `4`) and `temporal_tile_overlap` (default `1`).
LTX and Wan preserve causal state between temporal tiles. Hunyuan Video and TAEHV use overlap blending. MiniMax H3 keeps its model-specific fixed temporal windows because its latent-to-frame mapping is non-linear.
@@ -767,11 +769,11 @@ Example:
"vae_tiling_params": {
"enabled": false,
"temporal_tiling": false,
"tile_size_x": 0,
"tile_size_y": 0,
"tile_size_w": 0,
"tile_size_h": 0,
"target_overlap": 0.5,
"rel_size_x": 0.0,
"rel_size_y": 0.0,
"rel_size_w": 0.0,
"rel_size_h": 0.0,
"extra_tiling_args": ""
},
@@ -900,11 +902,11 @@ Other native fields:
| `vae_tiling_params` | `object` |
| `vae_tiling_params.enabled` | `boolean` |
| `vae_tiling_params.temporal_tiling` | `boolean` |
| `vae_tiling_params.tile_size_x` | `integer` |
| `vae_tiling_params.tile_size_y` | `integer` |
| `vae_tiling_params.tile_size_w` | `integer` |
| `vae_tiling_params.tile_size_h` | `integer` |
| `vae_tiling_params.target_overlap` | `number` |
| `vae_tiling_params.rel_size_x` | `number` |
| `vae_tiling_params.rel_size_y` | `number` |
| `vae_tiling_params.rel_size_w` | `number` |
| `vae_tiling_params.rel_size_h` | `number` |
| `vae_tiling_params.extra_tiling_args` | `string` |
| `cache_mode` | `string` |
| `cache_option` | `string` |
@@ -1115,11 +1117,11 @@ Example:
"vae_tiling_params": {
"enabled": false,
"temporal_tiling": false,
"tile_size_x": 0,
"tile_size_y": 0,
"tile_size_w": 0,
"tile_size_h": 0,
"target_overlap": 0.5,
"rel_size_x": 0.0,
"rel_size_y": 0.0,
"rel_size_w": 0.0,
"rel_size_h": 0.0,
"extra_tiling_args": ""
},
@@ -1240,11 +1242,11 @@ Other native fields:
| `vae_tiling_params` | `object` |
| `vae_tiling_params.enabled` | `boolean` |
| `vae_tiling_params.temporal_tiling` | `boolean` |
| `vae_tiling_params.tile_size_x` | `integer` |
| `vae_tiling_params.tile_size_y` | `integer` |
| `vae_tiling_params.tile_size_w` | `integer` |
| `vae_tiling_params.tile_size_h` | `integer` |
| `vae_tiling_params.target_overlap` | `number` |
| `vae_tiling_params.rel_size_x` | `number` |
| `vae_tiling_params.rel_size_y` | `number` |
| `vae_tiling_params.rel_size_w` | `number` |
| `vae_tiling_params.rel_size_h` | `number` |
| `vae_tiling_params.extra_tiling_args` | `string` |
| `cache_mode` | `string` |
| `cache_option` | `string` |
+4 -4
View File
@@ -78,11 +78,11 @@ static json make_vae_tiling_json(const sd_tiling_params_t& params) {
return {
{"enabled", params.enabled},
{"temporal_tiling", params.temporal_tiling},
{"tile_size_x", params.tile_size_x},
{"tile_size_y", params.tile_size_y},
{"tile_size_w", params.tile_size_w},
{"tile_size_h", params.tile_size_h},
{"target_overlap", params.target_overlap},
{"rel_size_x", params.rel_size_x},
{"rel_size_y", params.rel_size_y},
{"rel_size_w", params.rel_size_w},
{"rel_size_h", params.rel_size_h},
{"extra_tiling_args", params.extra_tiling_args ? params.extra_tiling_args : ""},
};
}