Stable WarpFusion v0.33 - Reconstructed Noise Updates
Added 2024-04-10 10:04:40 +0000 UTCLocal install guides:
Windows: https://github.com/Sxela/WarpFusion#local-installation-guide-for-windows-venv
Linux: https://github.com/Sxela/WarpFusion/blob/main/README.md#local-installation-guide-for-linux-ubuntu-2204-venv
If something's not working, make a new env and grab a fresh install.bat from that repo first, ask questions later :D
Changelog
enable fixed_code for style_strength = 1
automatically skip installation on Colab after the initial installation
add force_install option to override existing installation on Colab
replace fixed_code and use_predicted_noise with noise_mode dropdown
disable flow extraction when flow_warp is off
add predicted noise to AnimateDiff mode
add batched_adiff_rec_noise - batched mode for predicted noise in AnimateDiff mode (only works with batch_size == context_length for now)
add rec_separate_uc to process the unconditioned image in reconstructed noise mode separately (faster for AnimateDiff batched mode)
add disable_rec_noise_controlnets option for predicted noise (faster)
don't process negative prompt for rec_cfg == 1 (x2 faster)
add rec_steps_cutoff - predicted noise cutoff (fixes noisy outputs with style strength <1)
add rec_noise_scale - predicted noise scale setting (fixes noisy outputs with style strength <1)
fix Unicode characters destroying settings files
add new reconstructed noise options to GUI
set max rec_noise_pct to 2
now only overwrite rec noise in init source mode and when rec settings change or force overwrite is on
make rec source setting loadable
compare ControlNet settings separately in the compare settings cell
12.5.2024:
fix mask extraction error with mask source = 'none'
fix ipadapter light url
29.5.2024:
move to L
Noise mode dropdown
"fixed code" and "use predicted noise" checkboxes were replaced with the noise mode dropdown selector, as they can't be used simultaneously anyway, and enabling fixed code effectively disabled reconstructed noise.
Random mode means both "fixed code" and "use predicted noise" are off.
Reconstructed noise updates
Enabled Reconstructed noise for the AnimateDiff mode. Currently only works for batch size = context size.
rec_cfg = 1 should now render 2x faster.
disable_rec_noise_controlnets: doesn't use ControlNets during noise reconstruction. Is faster. Almost no visual difference if used with "controlnet" mode for controlnets.
rec_separate_uc - process unconditioned image counterpart separately. Saves Vram in animatediff mode.
rec_steps_cutoff - early stop noise reconstruction. May help if you're getting noisy results with style_strength < 1. May produce blurry results.
rec_noise_scale - same. Decrease if you're getting noise, increase if it's blurry.
rec_noise_pct capped by 2. You can now run noise reconstruction for more steps than the actual render to get better results, as it's much faster now.
Colab installation update
Successful installation on Google Colab cloud env now creates a lock file that will prevent it from reinstalling everything when you restart the env and run all.
You can still force reinstall, for example, if you somehow damaged the env later.
Local install guide:
https://github.com/Sxela/WarpFusion/blob/main/README.md
Guides made by users:
05.05.2023, v0.10 Video to AI Animation Tutorial For Beginners: Stable WarpFusion + Controlnet | MDMZ
11.05.2023, v0.11 How to use Stable Warp Fusion
13.05.2023, v0.8 Warp Fusion Local Install Guide (v0.8.6) with Diffusion Demonstration
14.05.2023, v0.12 Warp Fusion Alpha Masking Tutorial | Covers Both Auto-Masking and Custom Masking
23.05.2023, v0.12 STABLE WARPFUSION TUTORIAL - Colab Pro & Local Install
15.06.2023, v0.13 AI Animation out of Your Video: Stable Warpfusion Guide (Google Colab & Local Intallation)
17.06.2023, v0.14 Stable Warpfusion Tutorial: Turn Your Video to an AI Animation
21.06.2023, v0.14 Avoiding Common Problems with Stable Warpfusion
21.06.2023, v0.15 Warp Fusion: Step by Step Tutorial
04.07.2023, v0.15 Intense AI Video Maker (Stable WarpFusion Tutorial)
15.08.2023, v0.17 BEST Laptop for AI ( SDXL & Stable Warpfusion ) ft. RTX 4090 - Make AI Art FREE and FAST!
25.08.2023, ComfyWarp v0.1 WarpFusion: Warp and Consistency explanation in ComfyUI
2.09.2023, ComfyWarp v0.2 WarpFusion: ComfyWarp iteration 2.
3.09.2023, v0.16+ WarpFusion - Multiple Masked Prompts Guide
10.10.2023, ComfyWarp v0.4 WarpFusion: ComfyWarp v0.4.2 (schedulers, flow_blend)
4.11.2023, ComfyWarp v0.5 WarpFusion: ComfyWarp v0.5 - FixedQueue
13.11.2023, v0.27 Stable WarpFusion v0.27 - Changelog
YouTube playlist with settings:
https://www.youtube.com/watch?v=wvvcWm4Snmc&list=PL2cEnissQhlCUgjnGrdvYMwUaDkGemLGq
For tech support and other questions please join our discord server:
https://discord.gg/58Rd73uAe7
Discord is the preferred method because it is nearly impossible to provide any decent help or tech support via Patreon due to its limited text formatting and inability to add screenshots or videos to comments or DMs.
Due to the recent Patreon comments update it's impossible to reply to comments from notifications anymore, so if your comment hasn't been replied to for a while, DM me.
Comments
hey, i have this propblem: disabling init dummy for non-sdxl models Loading model from /content/drive/MyDrive/models/fcanimemixFcAnime_fcanimeV6.safetensors missing keys: ['betas', 'alphas_cumprod', 'alphas_cumprod_prev', 'sqrt_alphas_cumprod', 'sqrt_one_minus_alphas_cumprod', 'log_one_minus_alphas_cumprod', 'sqrt_recip_alphas_cumprod', 'sqrt_recipm1_alphas_cumprod', 'posterior_variance', 'posterior_log_variance_clipped', 'posterior_mean_coef1', 'posterior_mean_coef2', 'control_model.time_embed.0.weight', 'control_model.time_embed.0.bias', 'control_model.time_embed.2.weight', 'control_model.time_embed.2.bias', 'control_model.input_blocks.0.0.weight', 'control_model.input_blocks.0.0.bias', 'control_model.input_blocks.1.0.in_layers.0.weight', 'control_model.input_blocks.1.0.in_layers.0.bias', 'control_model.input_blocks.1.0.in_layers.2.weight', 'control_model.input_blocks.1.0.in_layers.2.bias', 'control_model.input_blocks.1.0.emb_layers.1.weight', 'control_model.input_blocks.1.0.emb_layers.1.bias', 'control_model.input_blocks.1.0.out_layers.0.weight', 'control_model.input_blocks.1.0.out_layers.0.bias', 'control_model.input_blocks.1.0.out_layers.3.weight', 'control_model.input_blocks.1.0.out_layers.3.bias', 'control_model.input_blocks.1.1.norm.weight', 'control_model.input_blocks.1.1.norm.bias', 'control_model.input_blocks.1.1.proj_in.weight', 'control_model.input_blocks.1.1.proj_in.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.ff.net.2.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.norm1.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.norm1.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.norm2.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.norm2.bias', 'control_model.input_blocks.1.1.transformer_blocks.0.norm3.weight', 'control_model.input_blocks.1.1.transformer_blocks.0.norm3.bias', 'control_model.input_blocks.1.1.proj_out.weight', 'control_model.input_blocks.1.1.proj_out.bias', 'control_model.input_blocks.2.0.in_layers.0.weight', 'control_model.input_blocks.2.0.in_layers.0.bias', 'control_model.input_blocks.2.0.in_layers.2.weight', 'control_model.input_blocks.2.0.in_layers.2.bias', 'control_model.input_blocks.2.0.emb_layers.1.weight', 'control_model.input_blocks.2.0.emb_layers.1.bias', 'control_model.input_blocks.2.0.out_layers.0.weight', 'control_model.input_blocks.2.0.out_layers.0.bias', 'control_model.input_blocks.2.0.out_layers.3.weight', 'control_model.input_blocks.2.0.out_layers.3.bias', 'control_model.input_blocks.2.1.norm.weight', 'control_model.input_blocks.2.1.norm.bias', 'control_model.input_blocks.2.1.proj_in.weight', 'control_model.input_blocks.2.1.proj_in.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.ff.net.2.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.norm1.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.norm1.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.norm2.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.norm2.bias', 'control_model.input_blocks.2.1.transformer_blocks.0.norm3.weight', 'control_model.input_blocks.2.1.transformer_blocks.0.norm3.bias', 'control_model.input_blocks.2.1.proj_out.weight', 'control_model.input_blocks.2.1.proj_out.bias', 'control_model.input_blocks.3.0.op.weight', 'control_model.input_blocks.3.0.op.bias', 'control_model.input_blocks.4.0.in_layers.0.weight', 'control_model.input_blocks.4.0.in_layers.0.bias', 'control_model.input_blocks.4.0.in_layers.2.weight', 'control_model.input_blocks.4.0.in_layers.2.bias', 'control_model.input_blocks.4.0.emb_layers.1.weight', 'control_model.input_blocks.4.0.emb_layers.1.bias', 'control_model.input_blocks.4.0.out_layers.0.weight', 'control_model.input_blocks.4.0.out_layers.0.bias', 'control_model.input_blocks.4.0.out_layers.3.weight', 'control_model.input_blocks.4.0.out_layers.3.bias', 'control_model.input_blocks.4.0.skip_connection.weight', 'control_model.input_blocks.4.0.skip_connection.bias', 'control_model.input_blocks.4.1.norm.weight', 'control_model.input_blocks.4.1.norm.bias', 'control_model.input_blocks.4.1.proj_in.weight', 'control_model.input_blocks.4.1.proj_in.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.ff.net.2.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.norm1.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.norm1.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.norm2.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.norm2.bias', 'control_model.input_blocks.4.1.transformer_blocks.0.norm3.weight', 'control_model.input_blocks.4.1.transformer_blocks.0.norm3.bias', 'control_model.input_blocks.4.1.proj_out.weight', 'control_model.input_blocks.4.1.proj_out.bias', 'control_model.input_blocks.5.0.in_layers.0.weight', 'control_model.input_blocks.5.0.in_layers.0.bias', 'control_model.input_blocks.5.0.in_layers.2.weight', 'control_model.input_blocks.5.0.in_layers.2.bias', 'control_model.input_blocks.5.0.emb_layers.1.weight', 'control_model.input_blocks.5.0.emb_layers.1.bias', 'control_model.input_blocks.5.0.out_layers.0.weight', 'control_model.input_blocks.5.0.out_layers.0.bias', 'control_model.input_blocks.5.0.out_layers.3.weight', 'control_model.input_blocks.5.0.out_layers.3.bias', 'control_model.input_blocks.5.1.norm.weight', 'control_model.input_blocks.5.1.norm.bias', 'control_model.input_blocks.5.1.proj_in.weight', 'control_model.input_blocks.5.1.proj_in.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.ff.net.2.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.norm1.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.norm1.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.norm2.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.norm2.bias', 'control_model.input_blocks.5.1.transformer_blocks.0.norm3.weight', 'control_model.input_blocks.5.1.transformer_blocks.0.norm3.bias', 'control_model.input_blocks.5.1.proj_out.weight', 'control_model.input_blocks.5.1.proj_out.bias', 'control_model.input_blocks.6.0.op.weight', 'control_model.input_blocks.6.0.op.bias', 'control_model.input_blocks.7.0.in_layers.0.weight', 'control_model.input_blocks.7.0.in_layers.0.bias', 'control_model.input_blocks.7.0.in_layers.2.weight', 'control_model.input_blocks.7.0.in_layers.2.bias', 'control_model.input_blocks.7.0.emb_layers.1.weight', 'control_model.input_blocks.7.0.emb_layers.1.bias', 'control_model.input_blocks.7.0.out_layers.0.weight', 'control_model.input_blocks.7.0.out_layers.0.bias', 'control_model.input_blocks.7.0.out_layers.3.weight', 'control_model.input_blocks.7.0.out_layers.3.bias', 'control_model.input_blocks.7.0.skip_connection.weight', 'control_model.input_blocks.7.0.skip_connection.bias', 'control_model.input_blocks.7.1.norm.weight', 'control_model.input_blocks.7.1.norm.bias', 'control_model.input_blocks.7.1.proj_in.weight', 'control_model.input_blocks.7.1.proj_in.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.ff.net.2.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.norm1.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.norm1.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.norm2.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.norm2.bias', 'control_model.input_blocks.7.1.transformer_blocks.0.norm3.weight', 'control_model.input_blocks.7.1.transformer_blocks.0.norm3.bias', 'control_model.input_blocks.7.1.proj_out.weight', 'control_model.input_blocks.7.1.proj_out.bias', 'control_model.input_blocks.8.0.in_layers.0.weight', 'control_model.input_blocks.8.0.in_layers.0.bias', 'control_model.input_blocks.8.0.in_layers.2.weight', 'control_model.input_blocks.8.0.in_layers.2.bias', 'control_model.input_blocks.8.0.emb_layers.1.weight', 'control_model.input_blocks.8.0.emb_layers.1.bias', 'control_model.input_blocks.8.0.out_layers.0.weight', 'control_model.input_blocks.8.0.out_layers.0.bias', 'control_model.input_blocks.8.0.out_layers.3.weight', 'control_model.input_blocks.8.0.out_layers.3.bias', 'control_model.input_blocks.8.1.norm.weight', 'control_model.input_blocks.8.1.norm.bias', 'control_model.input_blocks.8.1.proj_in.weight', 'control_model.input_blocks.8.1.proj_in.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.ff.net.2.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.norm1.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.norm1.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.norm2.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.norm2.bias', 'control_model.input_blocks.8.1.transformer_blocks.0.norm3.weight', 'control_model.input_blocks.8.1.transformer_blocks.0.norm3.bias', 'control_model.input_blocks.8.1.proj_out.weight', 'control_model.input_blocks.8.1.proj_out.bias', 'control_model.input_blocks.9.0.op.weight', 'control_model.input_blocks.9.0.op.bias', 'control_model.input_blocks.10.0.in_layers.0.weight', 'control_model.input_blocks.10.0.in_layers.0.bias', 'control_model.input_blocks.10.0.in_layers.2.weight', 'control_model.input_blocks.10.0.in_layers.2.bias', 'control_model.input_blocks.10.0.emb_layers.1.weight', 'control_model.input_blocks.10.0.emb_layers.1.bias', 'control_model.input_blocks.10.0.out_layers.0.weight', 'control_model.input_blocks.10.0.out_layers.0.bias', 'control_model.input_blocks.10.0.out_layers.3.weight', 'control_model.input_blocks.10.0.out_layers.3.bias', 'control_model.input_blocks.11.0.in_layers.0.weight', 'control_model.input_blocks.11.0.in_layers.0.bias', 'control_model.input_blocks.11.0.in_layers.2.weight', 'control_model.input_blocks.11.0.in_layers.2.bias', 'control_model.input_blocks.11.0.emb_layers.1.weight', 'control_model.input_blocks.11.0.emb_layers.1.bias', 'control_model.input_blocks.11.0.out_layers.0.weight', 'control_model.input_blocks.11.0.out_layers.0.bias', 'control_model.input_blocks.11.0.out_layers.3.weight', 'control_model.input_blocks.11.0.out_layers.3.bias', 'control_model.zero_convs.0.0.weight', 'control_model.zero_convs.0.0.bias', 'control_model.zero_convs.1.0.weight', 'control_model.zero_convs.1.0.bias', 'control_model.zero_convs.2.0.weight', 'control_model.zero_convs.2.0.bias', 'control_model.zero_convs.3.0.weight', 'control_model.zero_convs.3.0.bias', 'control_model.zero_convs.4.0.weight', 'control_model.zero_convs.4.0.bias', 'control_model.zero_convs.5.0.weight', 'control_model.zero_convs.5.0.bias', 'control_model.zero_convs.6.0.weight', 'control_model.zero_convs.6.0.bias', 'control_model.zero_convs.7.0.weight', 'control_model.zero_convs.7.0.bias', 'control_model.zero_convs.8.0.weight', 'control_model.zero_convs.8.0.bias', 'control_model.zero_convs.9.0.weight', 'control_model.zero_convs.9.0.bias', 'control_model.zero_convs.10.0.weight', 'control_model.zero_convs.10.0.bias', 'control_model.zero_convs.11.0.weight', 'control_model.zero_convs.11.0.bias', 'control_model.input_hint_block.0.weight', 'control_model.input_hint_block.0.bias', 'control_model.input_hint_block.2.weight', 'control_model.input_hint_block.2.bias', 'control_model.input_hint_block.4.weight', 'control_model.input_hint_block.4.bias', 'control_model.input_hint_block.6.weight', 'control_model.input_hint_block.6.bias', 'control_model.input_hint_block.8.weight', 'control_model.input_hint_block.8.bias', 'control_model.input_hint_block.10.weight', 'control_model.input_hint_block.10.bias', 'control_model.input_hint_block.12.weight', 'control_model.input_hint_block.12.bias', 'control_model.input_hint_block.14.weight', 'control_model.input_hint_block.14.bias', 'control_model.middle_block.0.in_layers.0.weight', 'control_model.middle_block.0.in_layers.0.bias', 'control_model.middle_block.0.in_layers.2.weight', 'control_model.middle_block.0.in_layers.2.bias', 'control_model.middle_block.0.emb_layers.1.weight', 'control_model.middle_block.0.emb_layers.1.bias', 'control_model.middle_block.0.out_layers.0.weight', 'control_model.middle_block.0.out_layers.0.bias', 'control_model.middle_block.0.out_layers.3.weight', 'control_model.middle_block.0.out_layers.3.bias', 'control_model.middle_block.1.norm.weight', 'control_model.middle_block.1.norm.bias', 'control_model.middle_block.1.proj_in.weight', 'control_model.middle_block.1.proj_in.bias', 'control_model.middle_block.1.transformer_blocks.0.attn1.to_q.weight', 'control_model.middle_block.1.transformer_blocks.0.attn1.to_k.weight', 'control_model.middle_block.1.transformer_blocks.0.attn1.to_v.weight', 'control_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.weight', 'control_model.middle_block.1.transformer_blocks.0.attn1.to_out.0.bias', 'control_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.weight', 'control_model.middle_block.1.transformer_blocks.0.ff.net.0.proj.bias', 'control_model.middle_block.1.transformer_blocks.0.ff.net.2.weight', 'control_model.middle_block.1.transformer_blocks.0.ff.net.2.bias', 'control_model.middle_block.1.transformer_blocks.0.attn2.to_q.weight', 'control_model.middle_block.1.transformer_blocks.0.attn2.to_k.weight', 'control_model.middle_block.1.transformer_blocks.0.attn2.to_v.weight', 'control_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.weight', 'control_model.middle_block.1.transformer_blocks.0.attn2.to_out.0.bias', 'control_model.middle_block.1.transformer_blocks.0.norm1.weight', 'control_model.middle_block.1.transformer_blocks.0.norm1.bias', 'control_model.middle_block.1.transformer_blocks.0.norm2.weight', 'control_model.middle_block.1.transformer_blocks.0.norm2.bias', 'control_model.middle_block.1.transformer_blocks.0.norm3.weight', 'control_model.middle_block.1.transformer_blocks.0.norm3.bias', 'control_model.middle_block.1.proj_out.weight', 'control_model.middle_block.1.proj_out.bias', 'control_model.middle_block.2.in_layers.0.weight', 'control_model.middle_block.2.in_layers.0.bias', 'control_model.middle_block.2.in_layers.2.weight', 'control_model.middle_block.2.in_layers.2.bias', 'control_model.middle_block.2.emb_layers.1.weight', 'control_model.middle_block.2.emb_layers.1.bias', 'control_model.middle_block.2.out_layers.0.weight', 'control_model.middle_block.2.out_layers.0.bias', 'control_model.middle_block.2.out_layers.3.weight', 'control_model.middle_block.2.out_layers.3.bias', 'control_model.middle_block_out.0.weight', 'control_model.middle_block_out.0.bias'] 352 unexpected keys: ['model_ema.decay', 'model_ema.num_updates', 'cond_stage_model.transformer.text_model.embeddings.position_ids'] 3 --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) in () 838 if 'animatediff' in model_version: 839 os.chdir(f'{root_dir}/animatediff') --> 840 from animatediff.models.motion_module import (get_motion_module, 841 TemporalTransformerBlock, TemporalTransformer3DModel) 842 os.chdir(f'{root_dir}/') 6 frames /usr/local/lib/python3.10/dist-packages/jax/_src/deprecations.py in getattr(name) 52 warnings.warn(message, DeprecationWarning, stacklevel=2) 53 return fn ---> 54 raise AttributeError(f"module {module!r} has no attribute {name!r}") 55 56 return getattr AttributeError: module 'jax.random' has no attribute 'KeyArray'
Toms Zarāns
2024-05-03 15:00:30 +0000 UTC
