build(deps): bump diffusers from 0.27.2 to 0.39.0 in /skills/remove-ai-marks/scripts - #13

Sourced from diffusers's releases.

Diffusers 0.39.0: New image and video pipelines, core library improvements, and more

New Pipelines

Cosmos 3

Cosmos 3 is NVIDIA's unified world foundation model (WFM) for Physical AI — a single omni-model built on a Mixture-of-Transformers (MoT) architecture that combines world generation, physical reasoning, and action generation, replacing the separate Predict, Reason, and Transfer models from earlier Cosmos releases. A single Cosmos3OmniTransformer runs a Qwen-style language model in parallel with a diffusion generation pathway, joined by a 3D multimodal RoPE. This release also lands video-to-video and action-conditioned generation, and a sound encoder.

• PR: huggingface/diffusers#13818
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/cosmos3

Thanks to @​atharvajoshi10, @​yzhautouskay, and @​MaciejBalaNV for the contributions.

Ideogram 4

Ideogram 4 is a flow-matching text-to-image model that uses a multimodal text encoder and an asymmetric classifier-free guidance scheme: a dedicated unconditional_transformer produces the negative branch with zeroed text features, while the main transformer consumes the full packed text + image sequence. The pipeline ships with structured prompt upsampling and LoRA loading support.

• PR: huggingface/diffusers#13859
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/ideogram4

Thanks to @​JinLiIdeogram for the contribution.

Krea 2

Krea 2 (K2) is a flow-matching text-to-image model built around a single-stream MMDiT with grouped-query attention. A Qwen3-VL text encoder provides the conditioning — hidden states from twelve decoder layers are tapped per token and fused inside the transformer by a small text-fusion stage — and images are decoded with the Qwen-Image VAE. Both the base (midtrain) and TDM (distilled, few-step) checkpoints are supported, alongside a LoRA DreamBooth trainer.

• PR: huggingface/diffusers#14045
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/krea2

Thanks to @​EleaZhong and @​Abhinay1997 for the contribution.

DreamLite

DreamLite is a text-to-image and image-editing model from ByteDance. It pairs a custom 2D U-Net (DreamLiteUNetModel) with the Qwen3-VL multimodal encoder as its prompt / image-instruction encoder, and uses an AutoencoderTiny (TAESD-style) VAE for fast latent encode/decode. A distilled DreamLiteMobilePipeline targets on-device, low-latency generation.

• PR: huggingface/diffusers#13815
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/dreamlite

Thanks to @​Carlofkl for the contribution.

PRX Pixel

PRXPixel is a pixel-space text-to-image generation model by Photoroom. A ~7B PRXTransformer2DModel denoises raw RGB images directly — no VAE is needed. The model is conditioned on a Qwen3-VL text encoder and uses flow matching where the transformer predicts the clean image at each step (x-prediction).

• PR: huggingface/diffusers#13928
• Docs: https://huggingface.co/docs/diffusers/main/api/pipelines/prx_pixel

Thanks to @​DavidBert for the contribution.

Motif-Video

... (truncated)

• a3608b5 Release: v0.39.0-release
• 72eb60c [tests] fix test_from_save_pretrained_dtype_inference (#13872)
• c412325 diffusers test installation package (#14078)
• 5dc153b support loading pipeline from transformer style (flat) repo (#14096)
• 761d72b Fix FA3 varlen wrapper when hub kernel returns single tensor (#14102)
• 9159a58 Fix mutable default args in lora_base.py (#14064)
• dbe1258 Bump transformers from 4.47.0 to 5.3.0 in /examples/cogview4-control (#14109)
• 0d32f80 [docs] fix qwen tokenizer in docstrings. (#14098)
• 1ffa423 ovis_image: fix guidance_scale / max_sequence_length / batched CFG / precompu...
• 26ec30e Ideogram4 lora training (#13861)
• Additional commits viewable in compare view