diff --git a/CHANGELOG.md b/CHANGELOG.md index 2d0cb6b41..65a7e9ba0 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,8 +2,8 @@ TODO: - Requires `diffusers==0.30.0` -- AlphaVLLM Lumina-Next: https://github.com/huggingface/diffusers/pull/8652 - LavenderFlow: https://github.com/huggingface/diffusers/pull/8796 +- - FlowMatchHeunDiscreteScheduler ## Update for 2024-07-05 @@ -12,10 +12,14 @@ TODO: with over 20 new pages and articles, now includes guides for nearly all major features thanks @GenesisArtemis! - support for [AlphaVLLM Lumina-Next-SFT](https://huggingface.co/Alpha-VLLM/Lumina-Next-SFT-diffusers) - note: this is a large model at 8.6GB and uses T5 XXL variation of text encoder + to use, simply select from *networks -> reference + use scheduler: default or euler flowmatch or heun flowmatch + note: this model uses T5 XXL variation of text encoder (previous version of Lumina used Gemma 2B as text encoder) - support for [HunyuanDiT 1.2](https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers) + to use, simply select from *networks -> reference - support for [CogFlorence 2 Large](https://huggingface.co/thwri/CogFlorence-2-Large-Freeze) VLM model + to use, simply select in process -> visual query - support for [AuraSR](https://huggingface.co/fal/AuraSR) high-quality 4x GAN-style upscaling model note: this is a large upscaler at 2.5GB - support for [uv](https://pypi.org/project/uv/), extremely fast installer, thanks @Yoinky3000! diff --git a/modules/model_lumina.py b/modules/model_lumina.py index 72bf04e2a..ca5f2e7b8 100644 --- a/modules/model_lumina.py +++ b/modules/model_lumina.py @@ -20,6 +20,5 @@ def load_lumina(_checkpoint_info, diffusers_load_config={}): cache_dir = shared.opts.diffusers_dir, **diffusers_load_config, ) - print('HERE2', diffusers_load_config) devices.torch_gc() return pipe diff --git a/modules/ui_common.py b/modules/ui_common.py index 1b8c5aade..f83e8594f 100644 --- a/modules/ui_common.py +++ b/modules/ui_common.py @@ -407,4 +407,6 @@ def update_token_counter(text, steps): ids = getattr(ids, 'input_ids', []) token_count = len(ids) - int(has_bos_token) - int(has_eos_token) max_length = shared.sd_model.tokenizer.model_max_length - int(has_bos_token) - int(has_eos_token) + if max_length is None or max_length < 0 or max_length > 10000: + max_length = 0 return f"{token_count}/{max_length}"