298977887/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-01-10 18:05:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix some more video tiled encode issues.
Some checks failed
Python Linting / Run Ruff (push) Successful in 1m50s
Details
Test server launches without errors / test (push) Failing after 1m5s
Details
Unit Tests / test (ubuntu-latest) (push) Failing after 1h23m5s
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.9, [self-hosted Linux], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.10, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.12, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-stable (12.1, --use-pytorch-cross-attention, macos, 3.9, [self-hosted macOS], stable) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Has been cancelled
Details
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, --use-pytorch-cross-attention, macos, 3.11, [self-hosted macOS], nightly) (push) Has been cancelled
Details
Unit Tests / test (macos-latest) (push) Has been cancelled
Details
Unit Tests / test (windows-latest) (push) Has been cancelled
Details

Browse Source 
The downscale_ratio formula for the temporal had issues with some frame
numbers.
This commit is contained in:
comfyanonymous 2024-12-19 23:14:03 -05:00
parent 52c1d933b2
commit cac68ca813
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
comfy/sd.py
View File

@ -12,6 +12,7 @@ from .ldm.audio.autoencoder import AudioOobleckVAE
import comfy.ldm.genmo.vae.model
import comfy.ldm.lightricks.vae.causal_video_autoencoder
import yaml
import math
import comfy.utils
@ -336,7 +337,7 @@ class VAE:
self.memory_used_decode = lambda shape, dtype: (1000 * shape[2] * shape[3] * shape[4] * (6 * 8 * 8)) * model_management.dtype_size(dtype)
self.memory_used_encode = lambda shape, dtype: (1.5 * max(shape[2], 7) * shape[3] * shape[4] * (6 * 8 * 8)) * model_management.dtype_size(dtype)
self.upscale_ratio = (lambda a: max(0, a * 6 - 5), 8, 8)
self.downscale_ratio = (lambda a: max(0, (a + 3) / 6), 8, 8)
self.downscale_ratio = (lambda a: max(0, math.floor((a + 5) / 6)), 8, 8)
self.working_dtypes = [torch.float16, torch.float32]
elif "decoder.up_blocks.0.res_blocks.0.conv1.conv.weight" in sd: #lightricks ltxv
self.first_stage_model = comfy.ldm.lightricks.vae.causal_video_autoencoder.VideoVAE()
@ -345,14 +346,14 @@ class VAE:
self.memory_used_decode = lambda shape, dtype: (900 * shape[2] * shape[3] * shape[4] * (8 * 8 * 8)) * model_management.dtype_size(dtype)
self.memory_used_encode = lambda shape, dtype: (70 * max(shape[2], 7) * shape[3] * shape[4]) * model_management.dtype_size(dtype)
self.upscale_ratio = (lambda a: max(0, a * 8 - 7), 32, 32)
self.downscale_ratio = (lambda a: max(0, (a + 4) / 8), 32, 32)
self.downscale_ratio = (lambda a: max(0, math.floor((a + 7) / 8)), 32, 32)
self.working_dtypes = [torch.bfloat16, torch.float32]
elif "decoder.conv_in.conv.weight" in sd:
ddconfig = {'double_z': True, 'z_channels': 4, 'resolution': 256, 'in_channels': 3, 'out_ch': 3, 'ch': 128, 'ch_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}
ddconfig["conv3d"] = True
ddconfig["time_compress"] = 4
self.upscale_ratio = (lambda a: max(0, a * 4 - 3), 8, 8)
self.downscale_ratio = (lambda a: max(0, (a + 2) / 4), 8, 8)
self.downscale_ratio = (lambda a: max(0, math.floor((a + 3) / 4)), 8, 8)
self.latent_dim = 3
self.latent_channels = ddconfig['z_channels'] = sd["decoder.conv_in.conv.weight"].shape[1]
self.first_stage_model = AutoencoderKL(ddconfig=ddconfig, embed_dim=sd['post_quant_conv.weight'].shape[1])