alphard/stable-diffusion.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: add lcm sampler support

Browse Source 
This referenced an issue discussion of the stable-diffusion-webui at
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13952, which
may not be too perfect.
This commit is contained in:
leejet 2023-11-17 22:50:06 +08:00
parent 3bf1665885
commit 536f3af672
5 changed files with 384 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
README.md
View File

@ -26,6 +26,7 @@ Inference of [Stable Diffusion](https://github.com/CompVis/stable-diffusion) in
- `DPM++ 2M`
- [`DPM++ 2M v2`](https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/8457)
- `DPM++ 2S a`
- [`LCM`](https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13952)
- Cross-platform reproducibility (`--rng cuda`, consistent with the `stable-diffusion-webui GPU RNG`)
- Embedds generation parameters into png output as webui-compatible text string
- Supported platforms
@ -80,6 +81,7 @@ git submodule update
```shell
cd models
pip install -r requirements.txt
# (optional) python convert_diffusers_to_original_stable_diffusion.py --model_path [path to diffusers weights] --checkpoint_path [path to weights]
python convert.py [path to weights] --out_type [output precision]
# For example, python convert.py sd-v1-4.ckpt --out_type f16
```
@ -132,7 +134,7 @@ arguments:
1.0 corresponds to full destruction of information in init image
-H, --height H image height, in pixel space (default: 512)
-W, --width W image width, in pixel space (default: 512)
--sampling-method {euler, euler_a, heun, dpm++2m, dpm++2mv2}
--sampling-method {euler, euler_a, heun, dpm++2m, dpm++2mv2, lcm}
sampling method (default: "euler_a")
--steps STEPS number of sample steps (default: 20)
--rng {std_default, cuda} RNG (default: cuda)
@ -196,3 +198,4 @@ docker run -v /path/to/models:/models -v /path/to/output/:/output sd [args...]
- [stable-diffusion-stability-ai](https://github.com/Stability-AI/stablediffusion)
- [stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
- [k-diffusion](https://github.com/crowsonkb/k-diffusion)
- [latent-consistency-model](https://github.com/luosiallen/latent-consistency-model)

9
examples/main.cpp
View File

@ -80,13 +80,16 @@ const char* sample_method_str[] = {
"dpm2",
"dpm++2s_a",
"dpm++2m",
"dpm++2mv2"};
"dpm++2mv2",
"lcm",
};
// Names of the sigma schedule overrides, same order as Schedule in stable-diffusion.h
const char* schedule_str[] = {
"default",
"discrete",
"karras"};
"karras"
};
struct Option {
int n_threads = -1;
@ -146,7 +149,7 @@ void print_usage(int argc, const char* argv[]) {
printf(" 1.0 corresponds to full destruction of information in init image\n");
printf(" -H, --height H image height, in pixel space (default: 512)\n");
printf(" -W, --width W image width, in pixel space (default: 512)\n");
printf(" --sampling-method {euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2}\n");
printf(" --sampling-method {euler, euler_a, heun, dpm2, dpm++2s_a, dpm++2m, dpm++2mv2, lcm}\n");
printf(" sampling method (default: \"euler_a\")\n");
printf(" --steps STEPS number of sample steps (default: 20)\n");
printf(" --rng {std_default, cuda} RNG (default: cuda)\n");

335
models/convert_diffusers_to_original_stable_diffusion.py Normal file
View File

@ -0,0 +1,335 @@
# Copy from https://github.com/huggingface/diffusers/blob/main/scripts/convert_diffusers_to_original_stable_diffusion.py
# LICENSE: https://github.com/huggingface/diffusers/blob/main/LICENSE
# Script for converting a HF Diffusers saved pipeline to a Stable Diffusion checkpoint.
# *Only* converts the UNet, VAE, and Text Encoder.
# Does not convert optimizer state or any other thing.
import argparse
import os.path as osp
import re
import torch
from safetensors.torch import load_file, save_file
# =================#
# UNet Conversion #
# =================#
unet_conversion_map = [
# (stable-diffusion, HF Diffusers)
("time_embed.0.weight", "time_embedding.linear_1.weight"),
("time_embed.0.bias", "time_embedding.linear_1.bias"),
("time_embed.2.weight", "time_embedding.linear_2.weight"),
("time_embed.2.bias", "time_embedding.linear_2.bias"),
("input_blocks.0.0.weight", "conv_in.weight"),
("input_blocks.0.0.bias", "conv_in.bias"),
("out.0.weight", "conv_norm_out.weight"),
("out.0.bias", "conv_norm_out.bias"),
("out.2.weight", "conv_out.weight"),
("out.2.bias", "conv_out.bias"),
]
unet_conversion_map_resnet = [
# (stable-diffusion, HF Diffusers)
("in_layers.0", "norm1"),
("in_layers.2", "conv1"),
("out_layers.0", "norm2"),
("out_layers.3", "conv2"),
("emb_layers.1", "time_emb_proj"),
("skip_connection", "conv_shortcut"),
]
unet_conversion_map_layer = []
# hardcoded number of downblocks and resnets/attentions...
# would need smarter logic for other networks.
for i in range(4):
# loop over downblocks/upblocks
for j in range(2):
# loop over resnets/attentions for downblocks
hf_down_res_prefix = f"down_blocks.{i}.resnets.{j}."
sd_down_res_prefix = f"input_blocks.{3*i + j + 1}.0."
unet_conversion_map_layer.append((sd_down_res_prefix, hf_down_res_prefix))
if i < 3:
# no attention layers in down_blocks.3
hf_down_atn_prefix = f"down_blocks.{i}.attentions.{j}."
sd_down_atn_prefix = f"input_blocks.{3*i + j + 1}.1."
unet_conversion_map_layer.append((sd_down_atn_prefix, hf_down_atn_prefix))
for j in range(3):
# loop over resnets/attentions for upblocks
hf_up_res_prefix = f"up_blocks.{i}.resnets.{j}."
sd_up_res_prefix = f"output_blocks.{3*i + j}.0."
unet_conversion_map_layer.append((sd_up_res_prefix, hf_up_res_prefix))
if i > 0:
# no attention layers in up_blocks.0
hf_up_atn_prefix = f"up_blocks.{i}.attentions.{j}."
sd_up_atn_prefix = f"output_blocks.{3*i + j}.1."
unet_conversion_map_layer.append((sd_up_atn_prefix, hf_up_atn_prefix))
if i < 3:
# no downsample in down_blocks.3
hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0.conv."
sd_downsample_prefix = f"input_blocks.{3*(i+1)}.0.op."
unet_conversion_map_layer.append((sd_downsample_prefix, hf_downsample_prefix))
# no upsample in up_blocks.3
hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
sd_upsample_prefix = f"output_blocks.{3*i + 2}.{1 if i == 0 else 2}."
unet_conversion_map_layer.append((sd_upsample_prefix, hf_upsample_prefix))
hf_mid_atn_prefix = "mid_block.attentions.0."
sd_mid_atn_prefix = "middle_block.1."
unet_conversion_map_layer.append((sd_mid_atn_prefix, hf_mid_atn_prefix))
for j in range(2):
hf_mid_res_prefix = f"mid_block.resnets.{j}."
sd_mid_res_prefix = f"middle_block.{2*j}."
unet_conversion_map_layer.append((sd_mid_res_prefix, hf_mid_res_prefix))
def convert_unet_state_dict(unet_state_dict):
# buyer beware: this is a *brittle* function,
# and correct output requires that all of these pieces interact in
# the exact order in which I have arranged them.
mapping = {k: k for k in unet_state_dict.keys()}
for sd_name, hf_name in unet_conversion_map:
mapping[hf_name] = sd_name
for k, v in mapping.items():
if "resnets" in k:
for sd_part, hf_part in unet_conversion_map_resnet:
v = v.replace(hf_part, sd_part)
mapping[k] = v
for k, v in mapping.items():
for sd_part, hf_part in unet_conversion_map_layer:
v = v.replace(hf_part, sd_part)
mapping[k] = v
new_state_dict = {v: unet_state_dict[k] for k, v in mapping.items()}
return new_state_dict
# ================#
# VAE Conversion #
# ================#
vae_conversion_map = [
# (stable-diffusion, HF Diffusers)
("nin_shortcut", "conv_shortcut"),
("norm_out", "conv_norm_out"),
("mid.attn_1.", "mid_block.attentions.0."),
]
for i in range(4):
# down_blocks have two resnets
for j in range(2):
hf_down_prefix = f"encoder.down_blocks.{i}.resnets.{j}."
sd_down_prefix = f"encoder.down.{i}.block.{j}."
vae_conversion_map.append((sd_down_prefix, hf_down_prefix))
if i < 3:
hf_downsample_prefix = f"down_blocks.{i}.downsamplers.0."
sd_downsample_prefix = f"down.{i}.downsample."
vae_conversion_map.append((sd_downsample_prefix, hf_downsample_prefix))
hf_upsample_prefix = f"up_blocks.{i}.upsamplers.0."
sd_upsample_prefix = f"up.{3-i}.upsample."
vae_conversion_map.append((sd_upsample_prefix, hf_upsample_prefix))
# up_blocks have three resnets
# also, up blocks in hf are numbered in reverse from sd
for j in range(3):
hf_up_prefix = f"decoder.up_blocks.{i}.resnets.{j}."
sd_up_prefix = f"decoder.up.{3-i}.block.{j}."
vae_conversion_map.append((sd_up_prefix, hf_up_prefix))
# this part accounts for mid blocks in both the encoder and the decoder
for i in range(2):
hf_mid_res_prefix = f"mid_block.resnets.{i}."
sd_mid_res_prefix = f"mid.block_{i+1}."
vae_conversion_map.append((sd_mid_res_prefix, hf_mid_res_prefix))
vae_conversion_map_attn = [
# (stable-diffusion, HF Diffusers)
("norm.", "group_norm."),
("q.", "query."),
("k.", "key."),
("v.", "value."),
("proj_out.", "proj_attn."),
]
def reshape_weight_for_sd(w):
# convert HF linear weights to SD conv2d weights
return w.reshape(*w.shape, 1, 1)
def convert_vae_state_dict(vae_state_dict):
mapping = {k: k for k in vae_state_dict.keys()}
for k, v in mapping.items():
for sd_part, hf_part in vae_conversion_map:
v = v.replace(hf_part, sd_part)
mapping[k] = v
for k, v in mapping.items():
if "attentions" in k:
for sd_part, hf_part in vae_conversion_map_attn:
v = v.replace(hf_part, sd_part)
mapping[k] = v
new_state_dict = {v: vae_state_dict[k] for k, v in mapping.items()}
weights_to_convert = ["q", "k", "v", "proj_out"]
for k, v in new_state_dict.items():
for weight_name in weights_to_convert:
if f"mid.attn_1.{weight_name}.weight" in k:
print(f"Reshaping {k} for SD format")
new_state_dict[k] = reshape_weight_for_sd(v)
return new_state_dict
# =========================#
# Text Encoder Conversion #
# =========================#
textenc_conversion_lst = [
# (stable-diffusion, HF Diffusers)
("resblocks.", "text_model.encoder.layers."),
("ln_1", "layer_norm1"),
("ln_2", "layer_norm2"),
(".c_fc.", ".fc1."),
(".c_proj.", ".fc2."),
(".attn", ".self_attn"),
("ln_final.", "transformer.text_model.final_layer_norm."),
("token_embedding.weight", "transformer.text_model.embeddings.token_embedding.weight"),
("positional_embedding", "transformer.text_model.embeddings.position_embedding.weight"),
]
protected = {re.escape(x[1]): x[0] for x in textenc_conversion_lst}
textenc_pattern = re.compile("|".join(protected.keys()))
# Ordering is from https://github.com/pytorch/pytorch/blob/master/test/cpp/api/modules.cpp
code2idx = {"q": 0, "k": 1, "v": 2}
def convert_text_enc_state_dict_v20(text_enc_dict):
new_state_dict = {}
capture_qkv_weight = {}
capture_qkv_bias = {}
for k, v in text_enc_dict.items():
if (
k.endswith(".self_attn.q_proj.weight")
or k.endswith(".self_attn.k_proj.weight")
or k.endswith(".self_attn.v_proj.weight")
):
k_pre = k[: -len(".q_proj.weight")]
k_code = k[-len("q_proj.weight")]
if k_pre not in capture_qkv_weight:
capture_qkv_weight[k_pre] = [None, None, None]
capture_qkv_weight[k_pre][code2idx[k_code]] = v
continue
if (
k.endswith(".self_attn.q_proj.bias")
or k.endswith(".self_attn.k_proj.bias")
or k.endswith(".self_attn.v_proj.bias")
):
k_pre = k[: -len(".q_proj.bias")]
k_code = k[-len("q_proj.bias")]
if k_pre not in capture_qkv_bias:
capture_qkv_bias[k_pre] = [None, None, None]
capture_qkv_bias[k_pre][code2idx[k_code]] = v
continue
relabelled_key = textenc_pattern.sub(lambda m: protected[re.escape(m.group(0))], k)
new_state_dict[relabelled_key] = v
for k_pre, tensors in capture_qkv_weight.items():
if None in tensors:
raise Exception("CORRUPTED MODEL: one of the q-k-v values for the text encoder was missing")
relabelled_key = textenc_pattern.sub(lambda m: protected[re.escape(m.group(0))], k_pre)
new_state_dict[relabelled_key + ".in_proj_weight"] = torch.cat(tensors)
for k_pre, tensors in capture_qkv_bias.items():
if None in tensors:
raise Exception("CORRUPTED MODEL: one of the q-k-v values for the text encoder was missing")
relabelled_key = textenc_pattern.sub(lambda m: protected[re.escape(m.group(0))], k_pre)
new_state_dict[relabelled_key + ".in_proj_bias"] = torch.cat(tensors)
return new_state_dict
def convert_text_enc_state_dict(text_enc_dict):
return text_enc_dict
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--model_path", default=None, type=str, required=True, help="Path to the model to convert.")
parser.add_argument("--checkpoint_path", default=None, type=str, required=True, help="Path to the output model.")
parser.add_argument("--half", action="store_true", help="Save weights in half precision.")
parser.add_argument(
"--use_safetensors", action="store_true", help="Save weights use safetensors, default is ckpt."
)
args = parser.parse_args()
assert args.model_path is not None, "Must provide a model path!"
assert args.checkpoint_path is not None, "Must provide a checkpoint path!"
# Path for safetensors
unet_path = osp.join(args.model_path, "unet", "diffusion_pytorch_model.safetensors")
vae_path = osp.join(args.model_path, "vae", "diffusion_pytorch_model.safetensors")
text_enc_path = osp.join(args.model_path, "text_encoder", "model.safetensors")
# Load models from safetensors if it exists, if it doesn't pytorch
if osp.exists(unet_path):
unet_state_dict = load_file(unet_path, device="cpu")
else:
unet_path = osp.join(args.model_path, "unet", "diffusion_pytorch_model.bin")
unet_state_dict = torch.load(unet_path, map_location="cpu")
if osp.exists(vae_path):
vae_state_dict = load_file(vae_path, device="cpu")
else:
vae_path = osp.join(args.model_path, "vae", "diffusion_pytorch_model.bin")
vae_state_dict = torch.load(vae_path, map_location="cpu")
if osp.exists(text_enc_path):
text_enc_dict = load_file(text_enc_path, device="cpu")
else:
text_enc_path = osp.join(args.model_path, "text_encoder", "pytorch_model.bin")
text_enc_dict = torch.load(text_enc_path, map_location="cpu")
# Convert the UNet model
unet_state_dict = convert_unet_state_dict(unet_state_dict)
unet_state_dict = {"model.diffusion_model." + k: v for k, v in unet_state_dict.items()}
# Convert the VAE model
vae_state_dict = convert_vae_state_dict(vae_state_dict)
vae_state_dict = {"first_stage_model." + k: v for k, v in vae_state_dict.items()}
# Easiest way to identify v2.0 model seems to be that the text encoder (OpenCLIP) is deeper
is_v20_model = "text_model.encoder.layers.22.layer_norm2.bias" in text_enc_dict
if is_v20_model:
# Need to add the tag 'transformer' in advance so we can knock it out from the final layer-norm
text_enc_dict = {"transformer." + k: v for k, v in text_enc_dict.items()}
text_enc_dict = convert_text_enc_state_dict_v20(text_enc_dict)
text_enc_dict = {"cond_stage_model.model." + k: v for k, v in text_enc_dict.items()}
else:
text_enc_dict = convert_text_enc_state_dict(text_enc_dict)
text_enc_dict = {"cond_stage_model.transformer." + k: v for k, v in text_enc_dict.items()}
# Put together new checkpoint
state_dict = {**unet_state_dict, **vae_state_dict, **text_enc_dict}
if args.half:
state_dict = {k: v.half() for k, v in state_dict.items()}
if args.use_safetensors:
save_file(state_dict, args.checkpoint_path)
else:
state_dict = {"state_dict": state_dict}
torch.save(state_dict, args.checkpoint_path)

38
stable-diffusion.cpp
View File

@ -3933,6 +3933,44 @@ class StableDiffusionGGML {
}
}
} break;
case LCM: // Latent Consistency Models
{
LOG_INFO("sampling using LCM method");
ggml_set_dynamic(ctx, false);
struct ggml_tensor* noise = ggml_dup_tensor(ctx, x);
struct ggml_tensor* d = ggml_dup_tensor(ctx, x);
ggml_set_dynamic(ctx, params.dynamic);
for (int i = 0; i < steps; i++) {
float sigma = sigmas[i];
// denoise
denoise(x, sigma, i + 1);
// x = denoised
{
float* vec_x = (float*)x->data;
float* vec_denoised = (float*)denoised->data;
for (int j = 0; j < ggml_nelements(x); j++) {
vec_x[j] = vec_denoised[j];
}
}
if (sigmas[i + 1] > 0) {
// x += sigmas[i + 1] * noise_sampler(sigmas[i], sigmas[i + 1])
ggml_tensor_set_f32_randn(noise, rng);
// noise = load_tensor_from_file(res_ctx, "./rand" + std::to_string(i+1) + ".bin");
{
float* vec_x = (float*)x->data;
float* vec_noise = (float*)noise->data;
for (int j = 0; j < ggml_nelements(x); j++) {
vec_x[j] = vec_x[j] + sigmas[i + 1] * vec_noise[j];
}
}
}
}
} break;
default:
LOG_ERROR("Attempting to sample with nonexisting sample method %i", method);

1
stable-diffusion.h
View File

@ -24,6 +24,7 @@ enum SampleMethod {
DPMPP2S_A,
DPMPP2M,
DPMPP2Mv2,
LCM,
N_SAMPLE_METHODS
};