PlagueKind - Minimax H3 - LTX2.3 Workflow - Ease of use - Eros | Sulphur Compatible | FaceID ## Minimax H3## V5.5 Notes- Major'ish Overhaul of the layout, and wiring.- Disabling Sparse falls back to comfy attention.Sparse Density Notes:0.80-0.85 - "match pytorch quality"0.9 - Default - Minimal Degredation 15-20% faster than 0.850.95 - HUGE boost for longer hi res generations, can introduce minor degredation## V5 Notes- I've added my Sparse attention node. No other speedups required. up to 2.5x speedup.- Switched to dareties lora. Use with shift 8/3 0.8 strength 6-8 steps. this lora works great for all modes.- Memory Chunking if you go to high with sparse, it causes slow down. for me beyond 2-4 caused slowdown on 16gb vram.- Don't mess with the sparse settings on the subgraph unless you have to.- Make sure to update my node pack to atleast 1.3.1- Make sure you're on the newest pytorch+cu combo supported.<hr />### SupportIf you find this project useful and want to support development:Monero (XMR):<pre><code>865BrcfWLdwELwuq5faV1uVTbh93zVK6AUYLY2c3mX6sFfAGRfS6axe1kBTYYKuM7ccN7zBZDAZvnT7E4NKmUazySdbpc7p</code></pre>## V4 Notes- Sage begone, welcome comfy attn. update comfyui, sage without sage issues.- Switched to 4 step 768 lora. Use with shift 6/3 0.8 strength 6-8 steps, or 1.0 with 4-6 steps.- Added hybrid model so you don't need to swap anymore, start with 25. 30 higher quality slightly less ref strength.- When ref swapping a video use er_sde/beta- Added original audio mode, avoids degradation and vae decode / Allows you to make music videos etc. it's in the reference subgraph.- Added minimax mode and mode selection to lora stack, so update node pack.## V3.1 Notes- Sage begone, welcome comfy attn. update comfyui, sage without sage issues.- Switched to 8 step new lora, these 2 new things combined behave very close to non turbo non sage.## V3 Notes- Added R2V mode.## V2.1 Notes- Added preview node.## V2 Notes- Added int8 convrot video vae- Kijai resized turbo lora, best at 0.6-0.7 strength.- Memory chunks return. huge speed up for me. 4 was pretty much the cap for 16gb vram.---## Requirements- [ComfyUI-PlagueKind-Nodes](<a target="_blank" rel="ugc" href="https://github.com/PlagueKind/Comfyui-PlagueKind-Nodes">https://github.com/PlagueKind/Comfyui-PlagueKind-Nodes</a>)- [ComfyUI-KJNodes](<a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">https://github.com/kijai/ComfyUI-KJNodes</a>)- [Rgthree-comfy](<a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">https://github.com/rgthree/rgthree-comfy</a>)- [Nvidia_RTX_Nodes_ComfyUI](<a target="_blank" rel="ugc" href="https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI">https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI</a>)- [ComfyUI-VideoHelperSuite](<a target="_blank" rel="ugc" href="https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite">https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite</a>)- [ComfyUI-H3-Motion-Context-MultiRef](<a target="_blank" rel="ugc" href="https://github.com/seitanism/ComfyUI-H3-Motion-Context-MultiRef">https://github.com/seitanism/ComfyUI-H3-Motion-Context-MultiRef</a>)---### Diffusion Model[minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models/resolve/main/minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors">https://huggingface.co/smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models/resolve/main/minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors</a>)[minimax_h3_hybrid_fl2va_ref2va_b30-49-int8.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models/resolve/main/minimax_h3_hybrid_fl2va_ref2va_b30-49-int8.safetensors">https://huggingface.co/smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models/resolve/main/minimax_h3_hybrid_fl2va_ref2va_b30-49-int8.safetensors</a>)### VAE[minimax_h3_audio_vae_fp32.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/vae/minimax_h3_audio_vae_fp32.safetensors</a>)[minimax_h3_video_vae_int8_convrot.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MiniMax-H3-experimental/resolve/main/minimax_h3_video_vae_int8_convrot.safetensors">https://huggingface.co/Kijai/MiniMax-H3-experimental/resolve/main/minimax_h3_video_vae_int8_convrot.safetensors</a>)[vae_approx/taeh3.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MiniMax-H3-TAE/resolve/main/vae_approx/taeh3.safetensors">https://huggingface.co/Kijai/MiniMax-H3-TAE/resolve/main/vae_approx/taeh3.safetensors</a>)### Text Encoder[qwen3vl_32b_minimax_h3_int8_convrot.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors">https://huggingface.co/Comfy-Org/MiniMax-H3/resolve/main/text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors</a>)### Frame Interpolation[film_net_fp16.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/frame_interpolation/resolve/main/frame_interpolation/film_net_fp16.safetensors">https://huggingface.co/Comfy-Org/frame_interpolation/resolve/main/frame_interpolation/film_net_fp16.safetensors</a>)### Turbo Lora[dareties_v4_step600_comfy_fro.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/MiniMax-H3_tests/resolve/main/minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro.safetensors">https://huggingface.co/silveroxides/MiniMax-H3_tests/resolve/main/minimax_h3_fl2v_lightx2v_v0.1_dareties_v4_step600_comfy_fro.safetensors</a>)supporting file required.make the folder h3_adaln in models.[h3_silu_temb_grid.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/deAPI-ai/minimax-h3-33b-int8/resolve/main/loras/h3_silu_temb_grid.safetensors">https://huggingface.co/deAPI-ai/minimax-h3-33b-int8/resolve/main/loras/h3_silu_temb_grid.safetensors</a>)---## V1.5 Notes- Added the option for T2V.- When using T2V, set scale mode of Target Dimension node to Dimensions (WxH) or you will get a square video.- Added FSR RCAS sharpening, 0.3 strength looks natural.- FFLF is unreliable at res above 640, don't know why, it's like this on default WF as well.- Target Dimension node controls the generation size only, refs are passed elsewhere.- Don't touch the other hidden resize nodes as they only control ref size and are set to max.- Euler + Linear Quadratic seems to be the best combo with between 15-20 steps.- I didn't add easy cache because it ruins the quality noticeably,- If you have time or a powerful card, try heunpp2 sampler. It's phenomenal.## LTX 2.3## V8 Notes- Updated everything to LTX 2.5.- Lora stack still seems to work.## V7 Notes- Added FaceID tracking.- Changed DMD Lora for smoother output.- Steps required 4-10. 6 seems good enough.- Pruna Video VAE for speed boost.- Int8 Convrot TE.- Any FPS choice seems to work.- Increase IMG Preprocess for extra movement.- ComfyUI broke subgraphs so I adapted.- Make sure you're on atleast 10s-nodes 1.9.6### SupportIf you find this project useful and want to support development:Monero (XMR):`865BrcfWLdwELwuq5faV1uVTbh93zVK6AUYLY2c3mX6sFfAGRfS6axe1kBTYYKuM7ccN7zBZDAZvnT7E4NKmUazySdbpc7p`Thank you for your support.## V6 Notes- Updated Eros to 1.4 much better.- You can disable all optional lora apart from distill and eros if you want. The others do enhance the output though.- Added Volume Boost option.- Using DMD for audio and video.- Use 0.715, 0.2412, 0.0 2x FPS sigma if you see jitter## V5 Notes- Using decoupled distillation for video and audio, and smaller loras. - REQUIRED.- Updated to Eros 1.3- FPS bumped to 30fps default.- 60fps native with 120fps via 2x now compatible.- Added an actually useable NVFP4 model, even though int8 convrot is more or less the same size and speed.- You can regain speed by disabling one of the optional loras, start with sulphur.## V4 Notes- New reference node injects reference directly into the model, mostly eliminating any drift.- New DMD distill lora, fixes issues of original distill which broke decompression method and prompt adherence, no need to write a paragraph anymore. Preprocess returns for enhanced movement.- Use 6-13 steps, default 8-9.- INT8 Triton VAE for fast decode.- INT8 Convrot added for increased speed on all cards.- JoyAI lora another lora similar to omninft, this helps adherence, dialog, interaction and more.- If using the nvfp4 transformer make sure to describe anatomy that isn't already visible in the image. I don't recommend using the nvfp4 text encoder for realism.---## V3 NotesTURN DOWN NEW EROS LORA TO 0.7 I SET IT AT 0.9 and it doesn't look correct like that.- Added Prompt Relay Node for advanced timeline prompting while keeping simplicity.- Added VHS save video. AV1/WEBM CRF0 produces virtually lossless video with extremely small file size.- Updated Eros Lora.- Moved RTX VSR into sampler graph.## V2 Notes- Upscale and 2x fps have added tiled sampler to improve speed. if you don't like the output, experiment with cfg pp sampler, or add 0.715 to sigma. Current sigma are done on purpose to retain identity and quality of first pass.## V1 Notes- Focused Mainly on Speed and ease of usability while retaining single pass quality and likeness.- First pass is more or less optimized.- Identity Retention is pretty good.- First pass balanced for speed and quality.- Upscale and 2x fps work but will be optimized later.- I would avoid using RTX VSR with the whole chain active unless you have like 96gb ram.- Nvfp4 models are only for Blackwell, using them will not save you speed if you don't have Blackwell, but they should still work.- Default settings of the first pass should produce good quality and sharp. I personally like to use this for a single pass and just render straight at 1280.- Bumped FPS to 30 because it looks way bettwen imo, quality seems clearer overall and it gets rid of that ltx base fps look.---## Memory Chunk Note- This saves vram and speeds up it/s especially on longer videos- With 16gb of VRAM 3 chunks seems optimal for me- If you get triton errors, enter the model loader subgraph and disable use triton kernels---## Requirements- [ComfyUI-PlagueKind-Nodes](<a target="_blank" rel="ugc" href="https://github.com/PlagueKind/Comfyui-PlagueKind-Nodes">https://github.com/PlagueKind/Comfyui-PlagueKind-Nodes</a>)- [ComfyUI-KJNodes](<a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">https://github.com/kijai/ComfyUI-KJNodes</a>)- [Rgthree-comfy](<a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">https://github.com/rgthree/rgthree-comfy</a>)- [10s-nodes](<a target="_blank" rel="ugc" href="https://github.com/TenStrip/10S-Comfy-nodes">https://github.com/TenStrip/10S-Comfy-nodes</a>)- [Nvidia_RTX_Nodes_ComfyUI](<a target="_blank" rel="ugc" href="https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI">https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI</a>)---### Model Choices[ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors</a>)### Latent Upscalers[ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors</a>)[ltx-2.5-latent-temporal-upscaler-x2-bf16-1.0.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-temporal-upscaler-x2-bf16-1.0.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-temporal-upscaler-x2-bf16-1.0.safetensors</a>)### VAE[ltx-2.5-audio-vae-bf16.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors</a>)[ltx-2.5-video-vae-conv-bf16.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-conv-bf16.safetensors</a>)### Text Encoder[gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors">https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors</a>)### FaceID LoRA[Best_FaceID_v1.0_LoRA.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Alissonerdx/LTX-Best-Face-ID/resolve/main/Best_FaceID_v1.0_LoRA.safetensors">https://huggingface.co/Alissonerdx/LTX-Best-Face-ID/resolve/main/Best_FaceID_v1.0_LoRA.safetensors</a>)### Optional LoRA[LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/LTX2.3_comfy/resolve/main/loras/LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors?download=true">https://huggingface.co/Kijai/LTX2.3_comfy/resolve/main/loras/LTX-2.3-OmniNFT-RL-Lora_bf16.safetensors?download=true</a>)[LTX_SulphurEXP_LoRA_fro99-avgrank105.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/maximsobolev275/LTX-SulphurExperimental-LoRA-Optimized/resolve/main/LTX_SulphurEXP_LoRA_fro99-avgrank105.safetensors">https://huggingface.co/maximsobolev275/LTX-SulphurExperimental-LoRA-Optimized/resolve/main/LTX_SulphurEXP_LoRA_fro99-avgrank105.safetensors</a>)[JoyAI-Echo-content_r256.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/TenStrip/LTX2.3_JoyAI_Lora_Extracted/resolve/main/JoyAI-Echo-content_r256.safetensors">https://huggingface.co/TenStrip/LTX2.3_JoyAI_Lora_Extracted/resolve/main/JoyAI-Echo-content_r256.safetensors</a>)[LTX_10Eros-v15_LoRA_fro99-avgrank103.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/maximsobolev275/LTX-10Eros-LoRA-r768/resolve/main/LTX_10Eros-v15_LoRA_fro99-avgrank103.safetensors">https://huggingface.co/maximsobolev275/LTX-10Eros-LoRA-r768/resolve/main/LTX_10Eros-v15_LoRA_fro99-avgrank103.safetensors</a>)### Optional Model converted by me[10Eros_v1_experimental_nvfp4.safetensors](<a target="_blank" rel="ugc" href="https://huggingface.co/Plaguekind/10Eros_v1_experimental_nvfp4/resolve/main/10Eros_v1_experimental_nvfp4.safetensors?download=true">https://huggingface.co/Plaguekind/10Eros_v1_experimental_nvfp4/resolve/main/10Eros_v1_experimental_nvfp4.safetensors?download=true</a>)

PlagueKind - Minimax H3 Sparse  Attention - LTX Workflow - Ease of use - Eros | Sulphur Compatible | FaceID

## V5 Notes- I've added my Sparse attention node. No other speedups required. up to 2.5x speedup.- Switched to dareties lora. Use with shift 8/3 0.8 strength 6-8 steps. this lora works great for all modes.- Memory Chunking disabled by default, if you go to high with sparse, it causes slow down. for me beyond 2-4 caused slowdown on 16gb vram.- Attention backend disabled by default, left in the mix for some reason atm lol.- Don't mess with the sparse settings on the subgraph unless you have to.- Make sure to update my node pack to atleast 1.3.1- Make sure you're on the newest pytorch+cu combo supported.

Files with SHA256: 0dd444e51429a6c20218887c09867ecf0b57dafe56c8b0ae8c765582c854c9f8