Minimax H3 INT8/INT4 Convrot Sampler settings I currently use are: er_sde/res_multistep simple Just uploaded both FL2VA &amp; REF2VA w4a8_mixed models quantized by Kijai. (Makes my mixed int4 models obsolete) True int4 model size with int8 activations, near int8 quality, same speed as int8. For RAM/VRAM-constrained systems. Update your ComfyUI to the latest version for support of the new w4a8 (Should be included in Stable ComfyUI v0.31.0 <a target="_blank" rel="ugc" href="https://github.com/Comfy-Org/ComfyUI/pull/15308">https://github.com/Comfy-Org/ComfyUI/pull/15308</a> FL2VA - first last (frame) to video / audio REF2VA - ref_images / ref_videos / ref_video_audios / ref_audios: up to 9 reference images, 3 reference videos (each may carry its own paired soundtrack), and 3 standalone reference audio clips Both models can generate t2v (Text to video), i2v (Image to video), v2v (Video to Video), a2v (Audio to video), and multiple references (image/video/audio). But were further fine-tuned/trained for higher-quality outputs for the intended use.

Minimax H3 INT8/INT4 ConvRot

minimax_h3_video_vae_fp16.safetensors

minimaxH3INT8INT4_fl2vaINT8Pruned.json

minimax_h3_audio_vae_fp32.safetensors

minimax_h3_ref2va_bf16.safetensors

minimaxH3INT8INT4_fl2vaINT8Pruned_txt.safetensors

minimax_h3_fl2va_pruned_int8_convrot.safetensors

minimax_h3_ref2va_int8_convrot.safetensors

minimaxH3INT8INT4_fl2vaINT8Pruned.safetensors

FL2VA INT8 Pruned

FL/REF2VA Pruned AsymW4A8

REF2VA INT4BQ Pruned

REF2VA INT4Q DEPRECATED

FL2VA INT4Q DEPRECATED

FL2VA INT4BQ Pruned

REF2VA INT8 Pruned

<a target="_blank" rel="ugc" href="https://hailuoai.video/">Hailuo H3</a> is the newest video generation model from <a target="_blank" rel="ugc" href="https://www.minimax.io/">MiniMax</a>, the Shanghai AI lab behind the Hailuo video app and the MiniMax text and audio model families. H3 generates native 2K video with synchronized audio in a single pass, at clip lengths up to 15 seconds. Developed by MiniMax. All credit for the model goes to the MiniMax team. You can use H3 two ways on Civitai: generate on-site against the hosted <a target="_blank" rel="ugc" href="https://platform.minimax.io/docs/guides/video-generation">MiniMax API</a> (the H3 (Api) version), or download the open weights from the H3 (Comfy) version on this page and run it yourself. The ComfyUI-format weights are also available from MiniMax and Comfy-Org on Hugging Face.<h3 id="background">Background</h3>MiniMax has shipped video models under the Hailuo name since 2024, moving from the I2V-01 series through Hailuo 02 and Hailuo 2.3. Those earlier models topped out around 1080p with fixed 6 or 10 second clips and no native sound. H3 is the step past that: it raises the ceiling to 2K, opens the clip length to any integer from 4 to 15 seconds, and folds audio generation into the same pass as the picture rather than bolting it on afterward.<h3 id="capabilities">Capabilities</h3>• Native 2K output (2560x1440 at 16:9) • Clips from 4 to 15 seconds, in one second increments • Synchronized audio generated with the video - dialogue, effects, and ambience timed to what is on screen • Text-to-video, image-to-video, and first frame plus last frame control • Omni-reference conditioning: up to 9 reference images, 3 reference video clips, and 3 reference audio clips • Multi-shot sequences and instruction-based editing<h3 id="on-civitai">On Civitai</h3>H3 is wired into the video generator across four workflows: Create Video (text only), Image to Video (single first frame), First/Last Frame (both endpoints), and Reference to Video (up to 9 reference images). Resolution is fixed at 2K because that is the only output H3 produces. Aspect ratio is selectable at 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16 for text prompts; when you supply a frame image, H3 adapts the framing to that image instead.Reference video and reference audio inputs are supported by the model but are not exposed in the Civitai form yet.<h3 id="notes">Notes</h3>H3 is a new model and MiniMax has not published a full spec sheet or a stable pricing page for it. Behavior and cost may shift as they finish the rollout. Prompt handling follows the usual MiniMax posture - this is a commercially hosted service and content is subject to the provider's policies, so expect refusals on material their API declines.<h3 id="links">Links</h3>• <a target="_blank" rel="ugc" href="https://platform.minimax.io/docs/guides/video-generation">MiniMax video generation docs</a> • <a target="_blank" rel="ugc" href="https://hailuoai.video/">Hailuo AI</a> • <a target="_blank" rel="ugc" href="https://www.minimax.io/">MiniMax</a> • <a target="_blank" rel="ugc" href="https://hailuoai.video/doc/terms-of-service.html">MiniMax Hailuo AI Terms of Service</a>

Files with SHA256: 8e505d95dd1561d47abd43d4238fd40d9bb1ae9e147ed0a4cba778d76ae4db48