Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

report full size for fast latents and update conversion matrix for v1.5

Browse Source
This commit is contained in:
damian0815
2022-11-02 01:18:50 +01:00
committed by Lincoln Stein
parent 00378e1ea6
commit 3f5bf7ac44
2 changed files with 42 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
ldm/invoke/generator/base.py
View File

@ -116,6 +116,29 @@ class Generator():
)
return Image.fromarray(x_sample.astype(np.uint8))
# write an approximate RGB image from latent samples for a single step to PNG
def sample_to_lowres_estimated_image(self,samples):
# origingally adapted from code by @erucipe and @keturn here:
# https://discuss.huggingface.co/t/decoding-latents-to-rgb-without-upscaling/23204/7
# these updated numbers for v1.5 are from @torridgristle
v1_5_latent_rgb_factors = torch.tensor([
# R G B
[ 0.3444, 0.1385, 0.0670], # L1
[ 0.1247, 0.4027, 0.1494], # L2
[-0.3192, 0.2513, 0.2103], # L3
[-0.1307, -0.1874, -0.7445] # L4
], dtype=samples.dtype, device=samples.device)
latent_image = samples[0].permute(1, 2, 0) @ v1_5_latent_rgb_factors
latents_ubyte = (((latent_image + 1) / 2)
.clamp(0, 1) # change scale from -1..1 to 0..1
.mul(0xFF) # to 0..255
.byte()).cpu()
return Image.fromarray(latents_ubyte.numpy())
def generate_initial_noise(self, seed, width, height):
initial_noise = None
if self.variation_amount > 0 or len(self.with_variations) > 0: