TCDScheduler advances the generator on the final step of a strength-truncated custom schedule

未关闭 适合新手
#15,288 2 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

维护者通常 1 天内回复

@SIDDARTHAREDDY8 已经在做这个了。

开始于 2026年11月15日。

  • #15301 来自 @SIDDARTHAREDDY8 —— 未关闭

评估

难度
2/5
预计耗时
1-3 小时
新手友好度
74/100
Issue 类型
缺陷
描述清晰度
描述清楚
活跃度
活跃
技术栈
python

调研方向

从 TCDScheduler 的 step 方法开始,其中最后一步的检查会将当前索引与 num_inference_steps 比较,然后在 eta > 0 时采样噪声。运行 issue 中的复现脚本,它使用 set_timesteps(timesteps=[999, 499, 19], strength=0.5),并确认生成器状态发生了变化。完成的标准是:检查使用 self.timesteps 的长度,在实际的最后一步生成器状态保持不变,并且现有的 TCD 调度器测试仍然通过。

由索引模型根据 Issue 内容生成。

描述

bug
Describe the bug

When TCDScheduler uses a non-empty custom timestep schedule truncated by
strength < 1, its actual final step advances the supplied random generator
when eta > 0.

For example, timesteps=[999, 499, 19] with strength=0.5 leaves only [19],
but num_inference_steps remains 3. The final-step check uses the original
step count and enters the noise-sampling branch.

In the tested case, the terminal output stays the same because the noise
coefficient is zero, but the generator state changes. Subsequent draws using
the same generator therefore differ.

I expected the actual final step to leave the generator state unchanged,
consistent with the scheduler's comment that noise is not used on the final
timestep.

A possible fix is to decide whether another step exists using the length of
self.timesteps. I have tested a candidate fix and can provide it for review.

Reproduction
import diffusers
import torch
from diffusers import TCDScheduler

print(f"torch={torch.__version__} diffusers={diffusers.__version__}")
print(f"source={diffusers.__file__}")

scheduler = TCDScheduler(prediction_type="sample")
scheduler.set_timesteps(timesteps=[999, 499, 19], strength=0.5, device="cpu")

generator = torch.Generator(device="cpu").manual_seed(0)
control = torch.Generator(device="cpu").manual_seed(0)
sample = torch.ones((1, 1), device="cpu")

before = generator.get_state().clone()
result = scheduler.step(
    torch.zeros_like(sample),
    scheduler.timesteps[0],
    sample,
    eta=0.3,
    generator=generator,
)
after = generator.get_state()

next_draw = torch.randn(4, generator=generator, device="cpu")
control_draw = torch.randn(4, generator=control, device="cpu")

print(f"actual timesteps={scheduler.timesteps.tolist()}")
print(f"num_inference_steps={scheduler.num_inference_steps}")
print(f"prev_sample={result.prev_sample.item()}")
print(f"pred_noised_sample={result.pred_noised_sample.item()}")
print(f"RNG state preserved: {torch.equal(before, after)}")
print(f"next draw: {next_draw.tolist()}")
print(f"control:   {control_draw.tolist()}")

assert torch.equal(before, after), "The terminal step advanced the generator"
Context

No response

Logs
Baseline: unmodified Diffusers source at commit
43e30028af5120d8b0868cb6975b9fad39cc4fab

torch=2.9.0+cu126
diffusers=0.44.0.dev0

actual timesteps=[19]
num_inference_steps=3
prev_sample=0.21879726648330688
pred_noised_sample=0.21879726648330688
RNG state preserved: False

next draw: [-0.293428897857666, -2.1787893772125244, 0.5684312582015991, -1.0845223665237427]
control:   [1.5409960746765137, -0.293428897857666, -2.1787893772125244, 0.5684312582015991]

AssertionError: The terminal step advanced the generator
System Info

Platform: Windows 11
Python: 3.12.8
PyTorch: 2.9.0+cu126
Diffusers: 0.44.0.dev0, source checkout at commit 43e30028af5120d8b0868cb6975b9fad39cc4fab
Device used for reproduction: CPU

Who can help?

No response

主要语言
Python
星标
34.9k
派生
7.5k
平均合并
3 天 16 小时
30 天内合并 PR
65

环境准备

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

huggingface/diffusers 的其他 Issue

查看 huggingface/diffusers 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。