LTX2 Rapid Merges GGUF

--- base_model: - Phr00t/LTX2-Rapid-Merges tags: - GGUF - quant - quantization - quantized - wip - untested - test - gguf pipeline_tag: image-text-to-video --- # LTX-2 Rapid GGUF > **Mirror of [3ndetz/LTX2-Rapid-Merges-GGUF](https://huggingface.co/3ndetz/LTX2-Rapid-Merges-GGUF).** Conversion and workflow by 3ndetz, base model by [Phr00t](https://huggingface.co/Phr00t/LTX2-Rapid-Merges). GGUF version of the original [LTX-2 Rapid](https://huggingface.co/Phr00t/LTX2-Rapid-Merges), converted in [colab](https://colab.research.google.com/drive/1b9un_g6vEFa-DWAV_kLImtWdXkqNZl2B?usp=sharing) (this is link to the jupyter notebook script) using city96 gguf convertion instructions with manual adding `config` field to metadata. ## Roadmap - [x] Quants with fixed config - [x] [GGUF version of workflow](https://huggingface.co/3ndetz/LTX2-Rapid-Merges-GGUF/blob/main/LTXV-DoAlmostEverything-v3-GGUF.json) - [ ] Demo videos for different quants on the same noise seed > If someone will provide a test result for different quants to compare, it will be too good! PR into this repo ## Developing If you're making custom ggufs, do not forget to add this to gguf metadata into the config string field: ```json {"transformer": {"_class_name": "AVTransformer3DModel", "_diffusers_version": "0.25.1", "activation_fn": "gelu-approximate", "attention_bias": true, "attention_head_dim": 128, "attention_type": "default", "caption_channels": 3840, "cross_attention_dim": 4096, "double_self_attention": false, "dropout": 0.0, "in_channels": 128, "norm_elementwise_affine": false, "norm_eps": 1e-06, "norm_num_groups": 32, "num_attention_heads": 32, "num_embeds_ada_norm": 1000, "num_layers": 48, "num_vector_embeds": null, "only_cross_attention": false, "cross_attention_norm": true, "out_channels": 128, "upcast_attention": false, "use_linear_projection": false, "qk_norm": "rms_norm", "standardization_norm": "rms_norm", "positional_embedding_type": "rope", "positional_embedding_theta": 10000.0, "positional_embedding_max_pos": [20, 2048, 2048], "timestep_scale_multiplier": 1000, "av_ca_timestep_scale_multiplier": 1000.0, "causal_temporal_positioning": true, "audio_num_attention_heads": 32, "audio_attention_head_dim": 64, "use_audio_video_cross_attention": true, "share_ff": false, "audio_out_channels": 128, "audio_cross_attention_dim": 2048, "audio_positional_embedding_max_pos": [20], "av_cros...

--- base_model: - Phr00t/LTX2-Rapid-Merges tags: - GGUF - quant - quantization - quantized - wip - untested - test - gguf pipeline_tag: image-text-to-video --- # LTX-2 Rapid GGUF GGUF version of the original [LTX-2 Rapid](https://huggingface.co/Phr00t/LTX2-Rapid-Merges), converted in [colab](https://colab.research.google.com/drive/1b9un_g6vEFa-DWAV_kLImtWdXkqNZl2B?usp=sharing) (this is link to the jupyter notebook script) using city96 gguf convertion instructions with manual adding `config` field to metadata. ## Roadmap - [x] Quants with fixed config - [x] [GGUF version of workflow](https://huggingface.co/3ndetz/LTX2-Rapid-Merges-GGUF/blob/main/LTXV-DoAlmostEverything-v3-GGUF.json) - [ ] Demo videos for different quants on the same noise seed > If someone will provide a test result for different quants to compare, it will be too good! PR into this repo ## Developing If you're making custom ggufs, do not forget to add this to gguf metadata into the config string field: ```json {"transformer": {"_class_name": "AVTransformer3DModel", "_diffusers_version": "0.25.1", "activation_fn": "gelu-approximate", "attention_bias": true, "attention_head_dim": 128, "attention_type": "default", "caption_channels": 3840, "cross_attention_dim": 4096, "double_self_attention": false, "dropout": 0.0, "in_channels": 128, "norm_elementwise_affine": false, "norm_eps": 1e-06, "norm_num_groups": 32, "num_attention_heads": 32, "num_embeds_ada_norm": 1000, "num_layers": 48, "num_vector_embeds": null, "only_cross_attention": false, "cross_attention_norm": true, "out_channels": 128, "upcast_attention": false, "use_linear_projection": false, "qk_norm": "rms_norm", "standardization_norm": "rms_norm", "positional_embedding_type": "rope", "positional_embedding_theta": 10000.0, "positional_embedding_max_pos": [20, 2048, 2048], "timestep_scale_multiplier": 1000, "av_ca_timestep_scale_multiplier": 1000.0, "causal_temporal_positioning": true, "audio_num_attention_heads": 32, "audio_attention_head_dim": 64, "use_audio_video_cross_attention": true, "share_ff": false, "audio_out_channels": 128, "audio_cross_attention_dim": 2048, "audio_positional_embedding_max_pos": [20], "av_cross_ada_norm": true, "use_embeddings_connector": true, "connector_attention_head_dim": 128, "connector_num_attention_heads": 30, "connector_num_layers": 2, "connector_positional_embedding_max_pos": [4096], "connect...

Source context: 229 downloads · 0 likes · Pipeline image-text-to-video · Repo Ne7/LTX2-Rapid-Merges-GGUF