← ImageLoRA · All LoRA guides
ai-toolkit vs SimpleTuner for MOSS Image LoRA training
Both ai-toolkit and SimpleTuner can train MOSS Image LoRAs. Here is how they compare, using each project's docs and GitHub activity.
| ai-toolkit | SimpleTuner |
|---|
| MOSS Image support | supported (SFT + Base, Oct 16; edit training Oct 17) | supported (v4.10.0, Oct 17; Base/SFT incl. edit LoRAs) |
|---|
| GitHub stars | 12321 | 2940 |
|---|
| Last commit | 2026-10-19 | 2026-10-18 |
|---|
| Latest release | none published | v4.10.1 |
|---|
| VRAM (MOSS Image) | Official (kohya sd-scripts guide; 1024px, batch 1, LoRA dim 16, AdamW, gradient checkpointing, text encoder outputs cached): ~13 GB training with bf16 DiT, ~9 GB with ConvRot INT8 DiT + text encoder, ~5-7 GB adding block swap (needs ~15 GB system RAM). Caching text encoder outputs needs ~8.3 GB even in INT8, so 8 GB GPUs are not supported yet. Training the text encoder LoRA too: ~17 GB INT8, ~32 GB bf16. SimpleTuner ships 24, 32, 48, 80 and 144 GB recipes at 512px. Community report (ai-toolkit): ~15 GB at batch 2, 1024px, AdamW [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026] |
|---|
| Overview | Ostris' trainer with a web UI and YAML configs; widest day-0 support for new image models. Community threads call it the easiest option for Flux/Krea. | bghira's trainer; community describes it as more powerful (e.g. teacher-student regularization) but with a harder data loader setup. |
|---|
ai-toolkit notes for MOSS Image
- Tokenizer loading bug fixed same day (Oct 16) in ai-toolkit; update before training
- Edit/reference LoRAs: SimpleTuner model_flavour sft-edit or base-edit with matching target and reference folders; ai-toolkit also trains Base and SFT as edit models
- Base LoRA with ai-toolkit defaults (adamw8bit, shift timesteps, rank 32) gave a good style by ~1,500 steps; Base-trained LoRAs also work on SFT [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- ComfyUI "lora key not loaded": ai-toolkit now saves unfused q/k/v LoRA keys (Oct 17); users fixed it with the official Comfy-Org MOSS files [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- ai-toolkit low_vram + cache_text_embeddings could OOM at startup because the text encoder stayed on the GPU; fixed in ai-toolkit on Oct 17, so update first
SimpleTuner notes for MOSS Image
- SimpleTuner recipes: rank-32 LoRA, LR 1e-4, REPA, 4,000 steps, 512px-area training; validate at 50 steps, CFG 3, 1024px
- Edit/reference LoRAs: SimpleTuner model_flavour sft-edit or base-edit with matching target and reference folders; ai-toolkit also trains Base and SFT as edit models
Which should you pick?
If you want the quickest start with a web UI, ai-toolkit is the usual community pick; choose a script-based trainer if you already use its ecosystem. We don't have a sourced head-to-head quality benchmark for MOSS Image between these two, so treat any "better results" claim as unknown.
Shared MOSS Image settings
- Learns fast [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- Tokenizer loading bug fixed same day (Oct 16) in ai-toolkit; update before training
- SFT variant: stripe artifacts reported, unresolved [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- sd-scripts: fp8_base is not supported for MOSS Image; use --convrot_int8 (and --convrot_int8_text_encoder) instead
- sd-scripts: --timestep_sampling sigma --weighting_scheme logit_normal --logit_mean -1.09 --logit_std 0.95 --discrete_flow_shift 1.0 reproduces pre-training; simpler alternative: --timestep_sampling shift --discrete_flow_shift 3.0
- sd-scripts example: LR 1e-4 constant at network_alpha 1 (lower LR if you raise alpha)
- SimpleTuner recipes: rank-32 LoRA, LR 1e-4, REPA, 4,000 steps, 512px-area training; validate at 50 steps, CFG 3, 1024px
- Edit/reference LoRAs: SimpleTuner model_flavour sft-edit or base-edit with matching target and reference folders; ai-toolkit also trains Base and SFT as edit models
- Base LoRA with ai-toolkit defaults (adamw8bit, shift timesteps, rank 32) gave a good style by ~1,500 steps; Base-trained LoRAs also work on SFT [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- May need a higher LoRA rank than usual (smaller hidden size than Krea 2); character LoRAs reported as hard to get right so far [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- Full fine-tunes on small datasets collapsed after a few epochs; use LoRA unless you have a very large dataset [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- ComfyUI "lora key not loaded": ai-toolkit now saves unfused q/k/v LoRA keys (Oct 17); users fixed it with the official Comfy-Org MOSS files [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
- ai-toolkit low_vram + cache_text_embeddings could OOM at startup because the text encoder stayed on the GPU; fixed in ai-toolkit on Oct 17, so update first
- Inference: an SFT LoRA at ~0.6 strength with the Base model at 30 steps, CFG 3 works well; 8-step DMD LoRAs exist for SFT and Base but can weaken LoRA effect [Discord community reports (AI Toolkit / banodoco / lodestone_rock servers), Oct 2026]
Setup guides
Where to rent a 16 GB+ GPU
Cheapest 16 GB+ cards (2026-10-16 14:43 UTC) from RunPod and Vast.ai. Prices move constantly; see the live price table.
| GPU | VRAM | RunPod community $/hr | Vast.ai cheapest $/hr |
|---|
| RTX A4000 | 16 GB | $0.17 | $0.09 |
| Tesla V100 | 16 GB | $0.19 | $0.10 |
| RTX 3090 | 24 GB | $0.22 | $0.12 |
| RTX 5060 Ti | 16 GB | — | $0.12 |
| RTX 5070 Ti | 16 GB | — | $0.12 |
| RTX A5000 | 24 GB | $0.16 | — |
Sources
FAQ
Is ai-toolkit or SimpleTuner better for MOSS Image?
Both support it. There is no sourced quality benchmark between them for this model yet; pick based on workflow (UI vs scripts) and the notes above.
Can I train MOSS Image LoRAs with ai-toolkit?
supported (SFT + Base, Oct 16; edit training Oct 17)
Can I train MOSS Image LoRAs with SimpleTuner?
supported (v4.10.0, Oct 17; Base/SFT incl. edit LoRAs)
Weekly newsletter: new models, trainer releases, cheapest GPUs.
Subscribe
Data updated 2026-10-16. Disclosure: RunPod and Vast.ai links are referral links; ImageLoRA may earn a commission at no cost to you. unknown = not yet verified from a source.