mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
Merge branch 'development' of https://github.com/pbaylies/stable-diffusion into development
This commit is contained in:
Peter Baylies
commit
e1f6ea2be7
@ -1,17 +1,30 @@
|
||||
# **Interactive Command-Line Interface**
|
||||
|
||||
The `dream.py` script, located in `scripts/dream.py`, provides an interactive interface to image generation similar to the "dream mothership" bot that Stable AI provided on its Discord server.
|
||||
The `dream.py` script, located in `scripts/dream.py`, provides an
|
||||
interactive interface to image generation similar to the "dream
|
||||
mothership" bot that Stable AI provided on its Discord server.
|
||||
|
||||
Unlike the txt2img.py and img2img.py scripts provided in the original CompViz/stable-diffusion source code repository, the time-consuming initialization of the AI model initialization only happens once. After that image generation
|
||||
from the command-line interface is very fast.
|
||||
Unlike the txt2img.py and img2img.py scripts provided in the original
|
||||
CompViz/stable-diffusion source code repository, the time-consuming
|
||||
initialization of the AI model initialization only happens once. After
|
||||
that image generation from the command-line interface is very fast.
|
||||
|
||||
The script uses the readline library to allow for in-line editing, command history (up and down arrows), autocompletion, and more. To help keep track of which prompts generated which images, the script writes a log file of image names and prompts to the selected output directory.
|
||||
The script uses the readline library to allow for in-line editing,
|
||||
command history (up and down arrows), autocompletion, and more. To
|
||||
help keep track of which prompts generated which images, the script
|
||||
writes a log file of image names and prompts to the selected output
|
||||
directory.
|
||||
|
||||
In addition, as of version 1.02, it also writes the prompt into the PNG file's metadata where it can be retrieved using scripts/images2prompt.py
|
||||
In addition, as of version 1.02, it also writes the prompt into the
|
||||
PNG file's metadata where it can be retrieved using
|
||||
scripts/images2prompt.py
|
||||
|
||||
The script is confirmed to work on Linux, Windows and Mac systems.
|
||||
|
||||
_Note:_ This script runs from the command-line or can be used as a Web application. The Web GUI is currently rudimentary, but a much better replacement is on its way.
|
||||
_Note:_ This script runs from the command-line or can be used as a Web
|
||||
application. The Web GUI is currently rudimentary, but a much better
|
||||
replacement is on its way.
|
||||
|
||||
|
||||
```
|
||||
(ldm) ~/stable-diffusion$ python3 ./scripts/dream.py
|
||||
@ -183,6 +196,56 @@ well as the --mask (-M) argument:
|
||||
| --init_mask <path> | -M<path> | None |Path to an image the same size as the initial_image, with areas for inpainting made transparent.|
|
||||
|
||||
|
||||
# Shortcuts
|
||||
|
||||
Since one so frequently refers back to a previously-generated seed or
|
||||
image, dream.py provides an easy shortcut that avoids having to cut
|
||||
and paste these values.
|
||||
|
||||
Here's how it works. Say you generated 6 images of a man-eating snail:
|
||||
|
||||
~~~~
|
||||
dream> man-eating snail -n6
|
||||
...
|
||||
>> Usage stats:
|
||||
>> 6 image(s) generated in 79.85s
|
||||
>> Max VRAM used for this generation: 3.36G. Current VRAM utilization:2.21G
|
||||
>> Max VRAM used since script start: 3.36G
|
||||
Outputs:
|
||||
[1] outputs/img-samples/000210.1414805682.png: "man-eating snail" -s50 -W512 -H512 -C7.5 -Ak_lms -S1414805682
|
||||
[2] outputs/img-samples/000210.3312885013.png: "man-eating snail" -s50 -W512 -H512 -C7.5 -Ak_lms -S3312885013
|
||||
[3] outputs/img-samples/000210.1398528919.png: "man-eating snail" -s50 -W512 -H512 -C7.5 -Ak_lms -S1398528919
|
||||
[4] outputs/img-samples/000210.92626031.png: "man-eating snail" -s50 -W512 -H512 -C7.5 -Ak_lms -S92626031
|
||||
[5] outputs/img-samples/000210.1733666373.png: "man-eating snail" -s50 -W512 -H512 -C7.5 -Ak_lms -S1733666373
|
||||
[6] outputs/img-samples/000210.2453524229.png: "man-eating snail" -s50 -W512 -H512 -C7.5 -Ak_lms -S2453524229
|
||||
~~~~
|
||||
|
||||
The last image generated (with seed 2453524229) looks really good. So let's
|
||||
pick that one for variation generation. Instead of cutting and pasting
|
||||
the argument -S2453524229, we can simply refer to the most recent seed as
|
||||
-1, and write:
|
||||
|
||||
~~~~
|
||||
dream> man-eating snail -v0.1 -n10 -S-1
|
||||
>> Reusing previous seed 2453524229
|
||||
...etc...
|
||||
~~~~
|
||||
|
||||
You can use -2 to refer to the second to last seed, -3 to the third to
|
||||
last, etc. It works with both individual images and grids. However,
|
||||
the numbering system only extends across the last group of images
|
||||
generated and doesn't reach back to earlier commands.
|
||||
|
||||
The initial image (-I or --init_img) argument works in a similar
|
||||
way. To use the second-to-most-recent snail image as the initial
|
||||
image for an img2img render, you could refer to it as -I-2:
|
||||
|
||||
~~~~
|
||||
dream> glowing science-fiction snail -I -2 -n4
|
||||
>> Reusing previous image outputs/img-samples/000213.2150458613.png
|
||||
...etc...
|
||||
~~~~
|
||||
|
||||
# Command-line editing and completion
|
||||
|
||||
If you are on a Macintosh or Linux machine, the command-line offers
|
||||
|
||||
@ -13,8 +13,9 @@ def choose_torch_device() -> str:
|
||||
def choose_autocast_device(device):
|
||||
'''Returns an autocast compatible device from a torch device'''
|
||||
device_type = device.type # this returns 'mps' on M1
|
||||
# autocast only supports cuda or cpu
|
||||
if device_type in ('cuda','cpu'):
|
||||
if device_type == 'cuda':
|
||||
return device_type,autocast
|
||||
elif device_type == 'cpu':
|
||||
return device_type,nullcontext
|
||||
else:
|
||||
return 'cpu',nullcontext
|
||||
|
||||
@ -111,7 +111,6 @@ class Generate:
|
||||
height = 512,
|
||||
sampler_name = 'k_lms',
|
||||
ddim_eta = 0.0, # deterministic
|
||||
precision = 'autocast',
|
||||
full_precision = False,
|
||||
strength = 0.75, # default in scripts/img2img.py
|
||||
seamless = False,
|
||||
@ -129,7 +128,6 @@ class Generate:
|
||||
self.sampler_name = sampler_name
|
||||
self.grid = grid
|
||||
self.ddim_eta = ddim_eta
|
||||
self.precision = precision
|
||||
self.full_precision = True if choose_torch_device() == 'mps' else full_precision
|
||||
self.strength = strength
|
||||
self.seamless = seamless
|
||||
|
||||
@ -121,30 +121,17 @@ class ResnetBlock(nn.Module):
|
||||
padding=0)
|
||||
|
||||
def forward(self, x, temb):
|
||||
h1 = x
|
||||
h2 = self.norm1(h1)
|
||||
del h1
|
||||
|
||||
h3 = nonlinearity(h2)
|
||||
del h2
|
||||
|
||||
h4 = self.conv1(h3)
|
||||
del h3
|
||||
h = self.norm1(x)
|
||||
h = nonlinearity(h)
|
||||
h = self.conv1(h)
|
||||
|
||||
if temb is not None:
|
||||
h4 = h4 + self.temb_proj(nonlinearity(temb))[:,:,None,None]
|
||||
h = h + self.temb_proj(nonlinearity(temb))[:,:,None,None]
|
||||
|
||||
h5 = self.norm2(h4)
|
||||
del h4
|
||||
|
||||
h6 = nonlinearity(h5)
|
||||
del h5
|
||||
|
||||
h7 = self.dropout(h6)
|
||||
del h6
|
||||
|
||||
h8 = self.conv2(h7)
|
||||
del h7
|
||||
h = self.norm2(h)
|
||||
h = nonlinearity(h)
|
||||
h = self.dropout(h)
|
||||
h = self.conv2(h)
|
||||
|
||||
if self.in_channels != self.out_channels:
|
||||
if self.use_conv_shortcut:
|
||||
@ -152,7 +139,7 @@ class ResnetBlock(nn.Module):
|
||||
else:
|
||||
x = self.nin_shortcut(x)
|
||||
|
||||
return x + h8
|
||||
return x + h
|
||||
|
||||
class LinAttnBlock(LinearAttention):
|
||||
"""to match AttnBlock usage"""
|
||||
@ -209,8 +196,7 @@ class AttnBlock(nn.Module):
|
||||
|
||||
h_ = torch.zeros_like(k, device=q.device)
|
||||
|
||||
device_type = 'mps' if q.device.type == 'mps' else 'cuda'
|
||||
if device_type == 'cuda':
|
||||
if q.device.type == 'cuda':
|
||||
stats = torch.cuda.memory_stats(q.device)
|
||||
mem_active = stats['active_bytes.all.current']
|
||||
mem_reserved = stats['reserved_bytes.all.current']
|
||||
@ -599,22 +585,16 @@ class Decoder(nn.Module):
|
||||
temb = None
|
||||
|
||||
# z to block_in
|
||||
h1 = self.conv_in(z)
|
||||
h = self.conv_in(z)
|
||||
|
||||
# middle
|
||||
h2 = self.mid.block_1(h1, temb)
|
||||
del h1
|
||||
|
||||
h3 = self.mid.attn_1(h2)
|
||||
del h2
|
||||
|
||||
h = self.mid.block_2(h3, temb)
|
||||
del h3
|
||||
h = self.mid.block_1(h, temb)
|
||||
h = self.mid.attn_1(h)
|
||||
h = self.mid.block_2(h, temb)
|
||||
|
||||
# prepare for up sampling
|
||||
device_type = 'mps' if h.device.type == 'mps' else 'cuda'
|
||||
gc.collect()
|
||||
if device_type == 'cuda':
|
||||
if h.device.type == 'cuda':
|
||||
torch.cuda.empty_cache()
|
||||
|
||||
# upsampling
|
||||
@ -622,33 +602,19 @@ class Decoder(nn.Module):
|
||||
for i_block in range(self.num_res_blocks+1):
|
||||
h = self.up[i_level].block[i_block](h, temb)
|
||||
if len(self.up[i_level].attn) > 0:
|
||||
t = h
|
||||
h = self.up[i_level].attn[i_block](t)
|
||||
del t
|
||||
|
||||
h = self.up[i_level].attn[i_block](h)
|
||||
if i_level != 0:
|
||||
t = h
|
||||
h = self.up[i_level].upsample(t)
|
||||
del t
|
||||
h = self.up[i_level].upsample(h)
|
||||
|
||||
# end
|
||||
if self.give_pre_end:
|
||||
return h
|
||||
|
||||
h1 = self.norm_out(h)
|
||||
del h
|
||||
|
||||
h2 = nonlinearity(h1)
|
||||
del h1
|
||||
|
||||
h = self.conv_out(h2)
|
||||
del h2
|
||||
|
||||
h = self.norm_out(h)
|
||||
h = nonlinearity(h)
|
||||
h = self.conv_out(h)
|
||||
if self.tanh_out:
|
||||
t = h
|
||||
h = torch.tanh(t)
|
||||
del t
|
||||
|
||||
h = torch.tanh(h)
|
||||
return h
|
||||
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user