New Model Request Reply

Workflow runs for New Model Request Reply

• DDPM schedulers add fresh noise on terminal transitions when the final timestep is nonzero

  skipped:
  New Model Request Reply#202:Issue#15139openedbysurgan12
  Oct 27, 20261s
  More actions for workflow run 202

• [Feature Request] Add DiCache for sample-adaptive caching in FLUX transformers

  skipped:
  New Model Request Reply#201:Issue#15134openedbyBlazeSR10hawk
  Oct 26, 20261s
  More actions for workflow run 201

• [Feature] Reuse Ulysses shard lengths across MiniMax-H3 blocks

  skipped:
  New Model Request Reply#200:Issue#15132openedbyLeslieWylie
  Oct 26, 20267s
  More actions for workflow run 200

• Flux2KleinInpaintPipeline: padding_mask_crop pastes a center crop of the result instead of resizing it

  skipped:
  New Model Request Reply#199:Issue#15131openedbyhkang4628
  Oct 26, 20261s
  More actions for workflow run 199

• set_adapters applies component weights only to the first adapter when broadcasting a dictionary

  skipped:
  New Model Request Reply#198:Issue#15127openedbygorkadabo1
  Oct 24, 20261s
  More actions for workflow run 198

• @dataclass on quant configs breaks __eq__/__repr__/hashing, and to_json_string() raises for most configs

  skipped:
  New Model Request Reply#197:Issue#15126openedbyOnePunchMonk
  Oct 24, 20269s
  More actions for workflow run 197

• Nunchaku AWQ config accepts any group_size, but the kernel only supports 64

  skipped:
  New Model Request Reply#196:Issue#15125openedbyOnePunchMonk
  Oct 24, 20261s
  More actions for workflow run 196

• Quantizer configs are mutated in place, leaking modules_to_not_convert across loads

  skipped:
  New Model Request Reply#195:Issue#15124openedbyOnePunchMonk
  Oct 24, 20261s
  More actions for workflow run 195

• from_single_file forces pre_quantized=True, breaking bnb/TorchAO/Quanto single-file loading

  skipped:
  New Model Request Reply#194:Issue#15123openedbyOnePunchMonk
  Oct 24, 20261s
  More actions for workflow run 194

• NVIDIAModelOptConfig.to_dict() crashes from_pretrained/save_pretrained when forward_loop is set

  skipped:
  New Model Request Reply#193:Issue#15122openedbyOnePunchMonk
  Oct 24, 202611s
  More actions for workflow run 193

• AutoRound: user-passed quantization_config silently overwrites checkpoint's quant settings

  skipped:
  New Model Request Reply#192:Issue#15120openedbyOnePunchMonk
  Oct 24, 20261s
  More actions for workflow run 192

• MiniMax-H3 creates full-clip FP32 temporaries after VAE decoding

  skipped:
  New Model Request Reply#191:Issue#15119openedbyLeslieWylie
  Oct 24, 20261s
  More actions for workflow run 191

• Training examples crash on --revision in expired non-EMA deprecation blocks

  skipped:
  New Model Request Reply#190:Issue#15115openedbySeverinVisionary
  Oct 23, 20261s
  More actions for workflow run 190

• [Model integration] Add Hy-Nomas support to Diffusers

  completed successfully:
  New Model Request Reply#189:Issue#15113openedbyjiaxiangc
  Oct 23, 20268s
  More actions for workflow run 189

• Text-to-image example updates EMA when AMP skips the optimizer step

  skipped:
  New Model Request Reply#188:Issue#15112openedbySeverinVisionary
  Oct 23, 20261s
  More actions for workflow run 188

• LMSDiscreteScheduler uses the wrong multistep order when sampling starts part-way through the schedule (img2img, inpainting)

  skipped:
  New Model Request Reply#187:Issue#15108openedbymottopanikeiku
  Oct 22, 20261m 30s
  More actions for workflow run 187

• encode_video truncates a fractional fps, so the video runs longer than its audio

  skipped:
  New Model Request Reply#186:Issue#15104openedbydevanshc777
  Oct 22, 20261s
  More actions for workflow run 186

• [modular] ConditionalPipelineBlocks should declare its own trigger inputs

  skipped:
  New Model Request Reply#183:Issue#15101openedbyyiyixuxu
  Oct 22, 20262s
  More actions for workflow run 183

• [modular] conditional block triggers should be workflow inputs

  skipped:
  New Model Request Reply#182:Issue#15100openedbyyiyixuxu
  Oct 22, 2026Skipped
  More actions for workflow run 182

• load_video returns mixed-mode frames for GIFs, breaking preprocess_video and AnimateDiff video-to-video

  skipped:
  New Model Request Reply#181:Issue#15098openedbynettanvirdev
  Oct 21, 202612s
  More actions for workflow run 181

• DEIS coefficient precision causes increasing error as inference steps increase

  skipped:
  New Model Request Reply#180:Issue#15090openedbyRobertboy18
  Oct 21, 20269s
  More actions for workflow run 180

• lr_scheduler step bug in examples code

  skipped:
  New Model Request Reply#179:Issue#15087openedbyweixiaohao
  Oct 20, 2026Skipped
  More actions for workflow run 179

• Error "cannot import name 'FqnToConfig' from 'torchao.quantization'" when importing the diffusers library on google colab

  skipped:
  New Model Request Reply#178:Issue#15085openedbyWiNE-iNEFF
  Oct 19, 20261s
  More actions for workflow run 178

• Qwen-Image 2.1 Turbo: VAE tiling introduces vertical streaks at 2048x2048 on NVIDIA/CUDA

  skipped:
  New Model Request Reply#177:Issue#15083openedbyReligious-J
  Oct 19, 20261s
  More actions for workflow run 177

• Follow-up to #14737: drop output_type="latent" from modular decode blocks

  skipped:
  New Model Request Reply#176:Issue#15071openedbyyiyixuxu
  Oct 17, 20262s
  More actions for workflow run 176