invoke-ai/InvokeAI

View on GitHub

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Stars: 28.2k
Forks: 3k
Open beginner issues: 0
Indexed issues: 327
Avg merge: 6d 5h
Merged PRs (30d): 19

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 15, 2026
Latest indexed: Sep 17, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue

Open All

327 open issues indexed

[bug]: Z-Image Base tensor size mismatch when using FLUX.2 Klein Qwen3 8B Encoder Open

bug

invoke-ai/InvokeAI#9526 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: The model manager fails to identify Ernie Image models and classifies them as "Unknown Model" Open

enhancement

invoke-ai/InvokeAI#9527 · 5 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: Model Manager imports Wan2.2-A14B VAE (single file) from local drive as an Anima VAE not available for Wan2.2 Open

bug

invoke-ai/InvokeAI#9528 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[enhancement]: Requesting addition of flash-attn and sage/sage2-attn optimizations in InvokeAI Open

7.0.0 enhancement

invoke-ai/InvokeAI#9529 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: InvokeAI AMD 96 GB Unified Memory / Windows ROCm Issue Open

bug

invoke-ai/InvokeAI#9530 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Bulk downloads scheduled before session expiry are lost: persist per account and replay after re-auth Open

invoke-ai/InvokeAI#9531 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Lost batch-mutation responses cannot repair persisted workspace references: needs server-side outcome reconciliation Open

invoke-ai/InvokeAI#9533 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Per-image mutation routes authorize and write in separate statements, so a revoked permission still applies Open

invoke-ai/InvokeAI#9534 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Gallery auto-select probe: no-op navigation discards the selection; quiet store clears it Open

invoke-ai/InvokeAI#9535 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Documentation: amdgpu lowered lockup_timeout in kernel 7.x affects InvokeAI Open

bug

invoke-ai/InvokeAI#9539 · 8 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
Changing your own password signs you out when a token refresh was accepted in the last 60s Open

invoke-ai/InvokeAI#9541 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: Multi-GPU generation intermittently stalls during l2i / post-denoise processing Open

bug

invoke-ai/InvokeAI#9546 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[enhancement]: Optional acceleration for non-distilled models Open

enhancement

invoke-ai/InvokeAI#9547 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[enhancement]: Default to Flashpack for v7 Open

enhancement

invoke-ai/InvokeAI#9548 · 2 comments · 1 reaction · 1 assignee · Indexed Sep 17, 2026
[bug]: Segment Anything V2 fails every time Open

bug

invoke-ai/InvokeAI#9551 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: Black images don't work for Inpaint Mask, Images less than 600px can't be used for Flux.2 Ref image Open

bug

invoke-ai/InvokeAI#9553 · 1 comment · 0 reactions · 1 assignee · Indexed Sep 17, 2026
ai-toolkit DoRA (.magnitude) adapters fail to load for every base except Krea-2 Open

invoke-ai/InvokeAI#9558 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[enhancement]: Add support for INT8 ConvRot quantized models (*_int8_convrot.safetensors) Open

enhancement

invoke-ai/InvokeAI#9559 · 0 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: FP4 Mistral 3 Text Encoder (for FLUX.2 DEV) May be Misconfigured Open

bug

invoke-ai/InvokeAI#9565 · 4 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: Potential Same CUDA Graphs Kernel Path Failure Problem as Llama CPP? (Proposed workaround included) Open

bug

invoke-ai/InvokeAI#9566 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[bug]: Official FLUX.2 Klein Qwen3 8B Encoder installs as Unknown; metadata update fails on macOS Open

bug

invoke-ai/InvokeAI#9567 · 2 comments · 0 reactions · 1 assignee · Indexed Sep 17, 2026
[enhancement]: Board Groups/Folders Open

enhancement

invoke-ai/InvokeAI#9574 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[bug]: Krea2 Inference is slow on MPS (due to hardcoded bfloat16 dtype) Open

bug

invoke-ai/InvokeAI#9575 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[enhancement]: Add video duration in seconds with automatic frame count calculation Open

invoke-ai/InvokeAI#9576 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[bug]: repo_name error when using starter SDQN model Open

bug

invoke-ai/InvokeAI#9580 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[bug]: Crashing Krea2 non-standard checkpoints after recent update. Open

bug

invoke-ai/InvokeAI#9585 · 9 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
[bug]: Every drag makes the window freeze until refresh since the last update Open

bug

invoke-ai/InvokeAI#9586 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026

invoke-ai/InvokeAI

Get new issues in your inbox