LTX2 Rapid Merges GGUF
GGUF version of the original LTX-2 Rapid, converted in colab (this is link to the jupyter notebook script) using city96 gguf convertion instructions with manual adding config field to metadata.
Model source
- Kind
- Other
- File size
- 8.07–35.2 GB
- Base model
- Phr00t/LTX2-Rapid-Merges
- Version
- vRevision 18bc90d
- Updated
- Oct 9, 2026
- Downloads
- 117
- Source
- Hugging Face
Source description
LTX-2 Rapid GGUF
GGUF version of the original LTX-2 Rapid, converted in colab (this is link to the jupyter notebook script) using city96 gguf convertion instructions with manual adding config field to metadata.
Roadmap
- Quants with fixed config
- GGUF version of workflow
- 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:
{"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], "connector_num_learnable_registers": 128, "connector_norm_output": true, "use_middle_indices_grid": true, "rope_type": "split", "frequencies_precision": "float64"}, "scheduler": {"_class_name": "RectifiedFlowScheduler", "_diffusers_version": "0.25.1", "num_train_timesteps": 1000, "shifting": null, "base_resolution": null, "sampler": "LinearQuadratic"}}
(config can change and should be taken from original to work properly)
Sources
1 source
Sources
1 sourceVerified Oct 9
Model artifacts
22 artifacts
Model artifacts
22 artifactsnsfw/ltx2-phr00tmerge-nsfw-v41/ltx2-phr00tmerge-nsfw-v41-F16.gguf
gguf · 35.2 GB · SHA-256 bd212c561a5a…3de0 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v41/ltx2-phr00tmerge-nsfw-v41-Q4_0.gguf
gguf · 10.6 GB · SHA-256 91b1eb144d09…19e8 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v41/ltx2-phr00tmerge-nsfw-v41-Q4_K_M.gguf
gguf · 11.8 GB · SHA-256 cd210876e343…90d3 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v41/ltx2-phr00tmerge-nsfw-v41-Q5_0.gguf
gguf · 12.7 GB · SHA-256 08f1cf403db3…4d53 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v41/ltx2-phr00tmerge-nsfw-v41-Q5_K_M.gguf
gguf · 13.2 GB · SHA-256 4aaf8651bee1…3954 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v41/ltx2-phr00tmerge-nsfw-v41-Q8_0.gguf
gguf · 19.0 GB · SHA-256 02b447346a3b…48ab · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-F16.gguf
gguf · 35.2 GB · SHA-256 849fc7dbf07a…a83e · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q3_K_M.gguf
gguf · 8.80 GB · SHA-256 79792dda7847…ce8a · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q3_K_S.gguf
gguf · 8.07 GB · SHA-256 60f5112c6368…ae19 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q3_K.gguf
gguf · 8.80 GB · SHA-256 79792dda7847…ce8a · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q4_0.gguf
gguf · 10.6 GB · SHA-256 cb40bda89720…c1a0 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q4_K_M.gguf
gguf · 11.8 GB · SHA-256 97fbc1303310…7405 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q5_0.gguf
gguf · 12.7 GB · SHA-256 0edb04ffb7ba…6778 · Hugging Face
Downloadnsfw/ltx2-phr00tmerge-nsfw-v62/ltx2-phr00tmerge-nsfw-v62-Q5_K_M.gguf
gguf · 13.2 GB · SHA-256 0e8e53c9ef96…1bca · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-F16.gguf
gguf · 35.2 GB · SHA-256 f25d16008f76…d12c · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q3_K_M.gguf
gguf · 8.80 GB · SHA-256 59006750bec0…8eec · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q3_K_S.gguf
gguf · 8.07 GB · SHA-256 69e20fa823d5…f948 · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q3_K.gguf
gguf · 8.80 GB · SHA-256 59006750bec0…8eec · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q4_0.gguf
gguf · 10.6 GB · SHA-256 48a094405895…9af6 · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q4_K_M.gguf
gguf · 11.8 GB · SHA-256 f8c1adf7b5da…de32 · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q5_0.gguf
gguf · 12.7 GB · SHA-256 0b32099d1728…6127 · Hugging Face
Downloadsfw/ltx2-phr00tmerge-sfw-v5/ltx2-phr00tmerge-sfw-v5-Q5_K_M.gguf
gguf · 13.2 GB · SHA-256 85a3c84256ba…b6ec · Hugging Face
DownloadSource excerpts
3 excerpts
Source excerpts
3 excerpts--- 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: 117 downloads · 0 likes · Pipeline image-text-to-video · Repo mukesh3444/LTX2-Rapid-Merges-GGUF
Source context: 60 downloads · 0 likes · Pipeline image-text-to-video · Repo mukesh3444/LTX2-Rapid-Merges-GGUF
