mirror of
https://github.com/huggingface/diffusers.git
synced 2026-01-27 17:22:53 +03:00
b88fef4785
* Add initial template * Second template * feat: Add TextEmbeddingModule to AnyTextPipeline * feat: Add AuxiliaryLatentModule template to AnyTextPipeline * Add bert tokenizer from the anytext repo for now * feat: Update AnyTextPipeline's modify_prompt method This commit adds improvements to the modify_prompt method in the AnyTextPipeline class. The method now handles special characters and replaces selected string prompts with a placeholder. Additionally, it includes a check for Chinese text and translation using the trans_pipe. * Fill in the `forward` pass of `AuxiliaryLatentModule` * `make style && make quality` * `chore: Update bert_tokenizer.py with a TODO comment suggesting the use of the transformers library` * Update error handling to raise and logging * Add `create_glyph_lines` function into `TextEmbeddingModule` * make style * Up * Up * Up * Up * Remove several comments * refactor: Remove ControlNetConditioningEmbedding and update code accordingly * Up * Up * up * refactor: Update AnyTextPipeline to include new optional parameters * up * feat: Add OCR model and its components * chore: Update `TextEmbeddingModule` to include OCR model components and dependencies * chore: Update `AuxiliaryLatentModule` to include VAE model and its dependencies for masked image in the editing task * `make style` * refactor: Update `AnyTextPipeline`'s docstring * Update `AuxiliaryLatentModule` to include info dictionary so that text processing is done once * simplify * `make style` * Converting `TextEmbeddingModule` to ordinary `encode_prompt()` function * Simplify for now * `make style` * Up * feat: Add scripts to convert AnyText controlnet to diffusers * `make style` * Fix: Move glyph rendering to `TextEmbeddingModule` from `AuxiliaryLatentModule` * make style * Up * Simplify * Up * feat: Add safetensors module for loading model file * Fix device issues * Up * Up * refactor: Simplify * refactor: Simplify code for loading models and handling data types * `make style` * refactor: Update to() method in FrozenCLIPEmbedderT3 and TextEmbeddingModule * refactor: Update dtype in embedding_manager.py to match proj.weight * Up * Add attribution and adaptation information to pipeline_anytext.py * Update usage example * Will refactor `controlnet_cond_embedding` initialization * Add `AnyTextControlNetConditioningEmbedding` template * Refactor organization * style * style * Move custom blocks from `AuxiliaryLatentModule` to `AnyTextControlNetConditioningEmbedding` * Follow one-file policy * style * [Docs] Update README and pipeline_anytext.py to use AnyTextControlNetModel * [Docs] Update import statement for AnyTextControlNetModel in pipeline_anytext.py * [Fix] Update import path for ControlNetModel, ControlNetOutput in anytext_controlnet.py * Refactor AnyTextControlNet to use configurable conditioning embedding channels * Complete control net conditioning embedding in AnyTextControlNetModel * up * [FIX] Ensure embeddings use correct device in AnyTextControlNetModel * up * up * style * [UPDATE] Revise README and example code for AnyTextPipeline integration with DiffusionPipeline * [UPDATE] Update example code in anytext.py to use correct font file and improve clarity * down * [UPDATE] Refactor BasicTokenizer usage to a new Checker class for text processing * update pillow * [UPDATE] Remove commented-out code and unnecessary docstring in anytext.py and anytext_controlnet.py for improved clarity * [REMOVE] Delete frozen_clip_embedder_t3.py as it is in the anytext.py file * [UPDATE] Replace edict with dict for configuration in anytext.py and RecModel.py for consistency * 🆙 * style * [UPDATE] Revise README.md for clarity, remove unused imports in anytext.py, and add author credits in anytext_controlnet.py * style * Update examples/research_projects/anytext/README.md Co-authored-by: Aryan <contact.aryanvs@gmail.com> * Remove commented-out image preparation code in AnyTextPipeline * Remove unnecessary blank line in README.md
75 lines
2.1 KiB
Python
75 lines
2.1 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
|
|
|
|
class Hswish(nn.Module):
|
|
def __init__(self, inplace=True):
|
|
super(Hswish, self).__init__()
|
|
self.inplace = inplace
|
|
|
|
def forward(self, x):
|
|
return x * F.relu6(x + 3.0, inplace=self.inplace) / 6.0
|
|
|
|
|
|
# out = max(0, min(1, slop*x+offset))
|
|
# paddle.fluid.layers.hard_sigmoid(x, slope=0.2, offset=0.5, name=None)
|
|
class Hsigmoid(nn.Module):
|
|
def __init__(self, inplace=True):
|
|
super(Hsigmoid, self).__init__()
|
|
self.inplace = inplace
|
|
|
|
def forward(self, x):
|
|
# torch: F.relu6(x + 3., inplace=self.inplace) / 6.
|
|
# paddle: F.relu6(1.2 * x + 3., inplace=self.inplace) / 6.
|
|
return F.relu6(1.2 * x + 3.0, inplace=self.inplace) / 6.0
|
|
|
|
|
|
class GELU(nn.Module):
|
|
def __init__(self, inplace=True):
|
|
super(GELU, self).__init__()
|
|
self.inplace = inplace
|
|
|
|
def forward(self, x):
|
|
return torch.nn.functional.gelu(x)
|
|
|
|
|
|
class Swish(nn.Module):
|
|
def __init__(self, inplace=True):
|
|
super(Swish, self).__init__()
|
|
self.inplace = inplace
|
|
|
|
def forward(self, x):
|
|
if self.inplace:
|
|
x.mul_(torch.sigmoid(x))
|
|
return x
|
|
else:
|
|
return x * torch.sigmoid(x)
|
|
|
|
|
|
class Activation(nn.Module):
|
|
def __init__(self, act_type, inplace=True):
|
|
super(Activation, self).__init__()
|
|
act_type = act_type.lower()
|
|
if act_type == "relu":
|
|
self.act = nn.ReLU(inplace=inplace)
|
|
elif act_type == "relu6":
|
|
self.act = nn.ReLU6(inplace=inplace)
|
|
elif act_type == "sigmoid":
|
|
raise NotImplementedError
|
|
elif act_type == "hard_sigmoid":
|
|
self.act = Hsigmoid(inplace)
|
|
elif act_type == "hard_swish":
|
|
self.act = Hswish(inplace=inplace)
|
|
elif act_type == "leakyrelu":
|
|
self.act = nn.LeakyReLU(inplace=inplace)
|
|
elif act_type == "gelu":
|
|
self.act = GELU(inplace=inplace)
|
|
elif act_type == "swish":
|
|
self.act = Swish(inplace=inplace)
|
|
else:
|
|
raise NotImplementedError
|
|
|
|
def forward(self, inputs):
|
|
return self.act(inputs)
|