Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

[bug]: Anima kohya LoRAs: layers outside the DiT blocks are not applied

Open Beginner friendly
  • Is something wrong?
#10,028 0 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 2 days

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
85/100
Issue type
Bug
Clarity
Clearly specified
Activity status
Active
Tech stack
python, pytorch
Domain
backend, machine-learning

Research direction

Start in invokeai/backend/patches/lora_conversions/anima_lora_conversion_utils.py at _convert_kohya_unet_key (line 80). Read the function and the provided repro script to see which keys stay flattened. Add mapping for final_layer_linear, final_layer_adaln_modulation_1, t_embedder_1_linear_1, x_embedder_proj_1 to their dotted forms. Run the snippet to confirm the layers list matches the expected dotted names.

Written by the indexing model from the issue text.

Description

bug
Is there an existing issue for this problem?
  • I have searched the existing issues
Install method

Manual (dev checkout)

Operating system

Windows

GPU vendor

Not GPU-specific (reproduced on CPU)

GPU model

No response

GPU VRAM

No response

Version number

main at 0ddc9df91b

What happened

In an Anima kohya LoRA, the layers outside the DiT blocks are never applied. _convert_kohya_unet_key (invokeai/backend/patches/lora_conversions/anima_lora_conversion_utils.py:80) only un-flattens blocks_N_… (and the llm_adapter_ prefix). Every other key keeps its flattened name: final_layer_linear, final_layer_adaln_modulation_1/2, t_embedder_1_linear_1/2, x_embedder_proj_1. The resulting dotted patch never resolves them, and each one logs "Failed to find module for LoRA layer key".

The LoRA still loads and works, just without those layers. That makes it weaker than trained, and the only signal is the per-layer warnings.

What you expected to happen

Non-block kohya keys map to final_layer.linear, final_layer.adaln_modulation.1, t_embedder.1.linear_1, x_embedder.proj.1 and so on, as the block keys do. A kohya parsing tree like the Krea-2 one (kohya_key_utils) would cover them.

How to reproduce the problem
import torch

import invokeai.backend.model_manager.load  # noqa: F401
from invokeai.backend.patches.lora_conversions.anima_lora_conversion_utils import lora_model_from_anima_state_dict


def lora(prefix: str) -> dict:
    return {f"{prefix}.lora_down.weight": torch.randn(4, 64), f"{prefix}.lora_up.weight": torch.randn(64, 4)}


sd = {}
for k in ("blocks_0_self_attn_q_proj", "final_layer_linear", "final_layer_adaln_modulation_1", "t_embedder_1_linear_1", "x_embedder_proj_1"):
    sd |= lora(f"lora_unet_{k}")
print(list(lora_model_from_anima_state_dict(sd, alpha=None).layers))

Output on main:

['lora_transformer-blocks.0.self_attn.q_proj', 'lora_transformer-final_layer_linear', 'lora_transformer-final_layer_adaln_modulation_1', 'lora_transformer-t_embedder_1_linear_1', 'lora_transformer-x_embedder_proj_1']
Additional context

In a LoRA trained on every layer these are 6 of 454 layers (about 1 % of the trained weights).

Found while checking every LoRA layout OneTrainer writes (b08db37) against main: OneTrainer's own savers run on meta-device models of the real architectures, then identification, LoRALoader and LayerPatcher module resolution on the InvokeAI model.

Discord username

No response

Dominant language
TypeScript
Stars
28.8k
Forks
3.1k
Avg merge
3d 4h
Merged PRs (30d)
161

Getting set up

  • No Dockerfile or Docker Compose file
  • Has a pull request template
  • No contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from invoke-ai/InvokeAI

All issues in invoke-ai/InvokeAI

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.