News about the DAZ Studio and Poser software

Monthly Archives: August 2026

Minimax H3 watercolour example

Posted on by Posted in The Animation Industry, Tutorials Leave a comment

An example of one of the appealing visual styles possible with the new Minimax H3…

 

Text to video, a quick test at 0.5 megapixel quality, with Nvidia’s official RTX upscaling (so quick, who knew?) to 1440px. Audio is a bit wobbly, but a finished storytelling movie would replace narration, SFX and music.

The prompt’s starting line, to set the visual style:

integrated_multimodal_description: 2D-animated in a European watercolor storybook style with deep indigo night washes and silver moonlight highlights.

Other strong possibilities that are related:

2D-animated in a European watercolor storybook style

2D-animated in soft painterly children’s-book watercolor style

2D-animated in warm hand-painted whimsical style

Note the American spelling of watercolor.

I’ve yet to test the reference model, where you can input character-sheets etc.

Updated: My Minimax workflow for the 3060 12Gb card

Posted on by Posted in Freebies, The Animation Industry, Tutorials Leave a comment

More success with Minimax H3 video generation.


 

At 1504 pixels, five seconds.

The workflow I’m using is now at version 1.4. Please update, if it’s been of interest to you.

Download: MiniMax_H3_megaworkflow-3060-12Gb-v14.zip

I’ve deleted the old GGUF posts and workflow. The above is far better.

I accidentally generated a test at 2.0 (1920px), and it can be done on a 3060 card, but is best left at 3 or 4 seconds. 7 seconds will take 35+ minutes.

 

This is text prompt to video. Upscaling can be done by extracting the first and last frame and re-using them as start and end points. That way you more or less get what the draft showed, even though you’ve moved up from 0.4 to 2.0 in megapixels. This roundtrip is now included in the new workflow.

Next up, sorting out a Minimax Music workflow. Then testing the Minimax reference to video model, with Poser renders.

Success – Minimax H3 video at 1376 x 768px, on a 3060 12Gb card

Posted on by Posted in Companion software, Freebies, The Animation Industry, Tutorials Leave a comment

Hurrah, success with Minimax text-to-video on my RTX 3060 card! I can now generate video to Minimax’s 1.0 resolution. The sweet spot seems to be 12 minutes to get a seven second video at 0.9 resolution.

Windows 11, RTX 3060 12Gb with just 24Gb DDR3 system RAM (most people run 32Gb of DDR4). It’s amazing I can do large coherent videos on this, in a few minutes, on an old server. How far we’ve come since the days when Stable Diffusion 1.5 was mostly gloopy mis-fires at 512px, and took ages.

Minimax’s prompt adherence is now much better, now I’ve moved on from using a supercrushed Q2 GGUF for the prompt-processing. Next step is to see how well it works in combination with Poser / natural media emulation. But for now, a full setup tutorial.

TUTORIAL:

Here’s how to do it on this humble entry-level card, with the latest software, file-types and turbo boosters. The workflow is linked at the bottom of the post. All free, as is the way with generative AI.

First, install a new ComfyUI Portable, then use the Manager to update ComfyUI to the latest 0.32.x or higher (needed!). If the ComfyUI console throws a polars error from Python when starting up, then also pip install polars-lts-cpu (it’s polars for older CPUs, which lack the latest whizz-bang multimedia processing extensions).

Second, clear 40Gb of space on the SSD for the files you need, and also leave plenty of headroom for the Windows swap-file etc. I have my swap-file capped at 24Gb to match the system RAM.

Models: At HF get minimax_h3_fl2va_pruned-w4a8_convrot_pruned.safetensors (11.6Gb) and minimax_h3_ref2va_pruned-w4a8_convrot_pruned.safetensors (11.6Gb). The first does text-to-video and first frame or first frame/last frame. The second takes character / environment reference images (e.g. Poser character renders), and combines the character(s) and scenes into the video, if you have the prompting done correctly. Correct prompting is everything with Minimax H3. Put the files in ..\ComfyUI\models\diffusion_models\

Clip: At HF get qwen3vl_32b_minimax_h3-w4a8_convrot.safetensors (14.6Gb). Put the file in ..\models\text_encoders\

The above are Winnougan’s highly efficient ‘pruned’ blends of the FP4 and Int8 format, suitable for the 3060 12Gb card and matched with the very latest ComfyUI features.

VAE video: At HF get Kijai’s minimax_h3_video_vae_int8_convrot.safetensors (3.7Gb). This decodes the video frames into a video, and is far faster than the original. Place the file in ..\ComfyUI\models\vae\

VAE audio: At HF get minimax_h3_audio_vae_fp32.safetensors (577Mb). This is the standard from ComfyUI, and works so quickly it’s not worth speeding up. Place the file in ..\ComfyUI\models\vae\

Turbo LoRA: At HF get Abiray’s minimax_h3_turbo_4step_ckpt600_V4.safetensors turbo LoRA (590Mb) and place it in ..\ComfyUI\models\loras\

Having ComfyUI at version 0.32.0 or higher allows you to run the turbo video VAE and also to pair the turbo LoRA with their new ‘Sage Attention replacement’ speed-up called Comfy Kitchen Attention. Simply add their new ModelAttentionBackend node between the model and the LoRA, and toggle it to use ‘Kitchen Attention’. That’s it, though note it’s best for lower-end cards and that 50-series cards may not see much difference. I think I’m getting a 20-30% speed-up from it.

With this setup I get good results at 5 steps with the turbo LoRA at 1.2, Euler / beta. Image quality is still slightly crispy and granulated, but better than smushed and gloopy. The crispiness could be because I’m over-forcing the turbo LoRA, of course.

7 mins = 7 seconds, at 0.6 (1056 x 608px).
12 mins = 7 seconds, at 0.9 (1280 x 736px).
18 mins = 8 seconds, at 1.0 (1376 x 768px) (the model’s native trained resolution) and using 6 steps.

All 24fps at 16:9 widescreen ratio. 0.9 seems the sweet spot for me re: the balance of time / quality / size. That’s the video which heads this tutorial.

Workflow as a .JSON file for ComfyUI: MiniMax_H3_megaworkflow-3060-12Gb-v14.zip (updated, 15th Aug).

New for Poser and DAZ and more, July 2026

Posted on by Posted in Companion software, DAZ Studio, Freebies, Poser Leave a comment

I’m getting back of track for an end-of-month post, so here’s my regular personal pick of Poser and DAZ Studio items recently released. Plus links to interesting software, tutorials etc. Just two weeks worth of goodies, this time, since the last survey went to the middle of July.

Science fiction:

A simple scene from 1971s, Tunnel of Technomages for Poser.

Alien plants are always welcome. Fantasy Plants of de Altus Saltus, by quality plant maker Martin J. Frost.

Horror:

Gothic Gargoyles including a waterspout that would also suit steampunk street scenes.

Fantasy:

* A well-designed ‘Conan-era’ style Sacrificial Ritual Dagger Prop with Poses.

Sacrificial Ritual Book Prop with Poses. Also a Sacrificial Stone Altar Prop.

Need even more mediaeval stuff for your runtime? Powerage has 130 Medieval Props Collection for DAZ, currently at a bargain $10. AI-generated 3D props, but good enough for background clutter.

Storybook:

Lyra Character for DAZ, from 3DUniverse.

Summer Vibes props for Poser and DAZ.

SV’s Whimsical Flowers.

80s Heart Galore Earrings.

Ice Cream Configurator for DAZ.

Toon:

JAF Pear for DAZ.

3DUniverse are now selling on Renderosity. Only the Lyra Character for DAZ and accessories, at present (see above). But they say… “The Entire 3DUniverse Catalog of Products will be added in the coming weeks!”. Which should mean all the toons.

Figures and parts:

dForce Timmy Hair for Genesis 9. Convincing boy hair, which you don’t see every day. Could also suit imps and similar smaller fantasy figures.

Free Moon Men Poses for Genesis 8/8.1, for a classic pulp art scene.

C66 Figure Splitter. A script set to convert 3D figures and props into kitbash / greeble libraries.

Animals:

Terror Bird by AM. A prehistoric bird from the Miocene megafauna era. Very savage apparently, and not a friendly cute duckie.

Landscape:

Arboreal Pond Exocab for near-future pond living. Just invent an electrostatic force-field to keep the insects out!

Historical:

* Babylonian Priestess for Genesis 8 Female. Apparently authentic.

* Lots of free 20th century industrial props for Poser, from TryNationArtist71.

Shaders:

Free ODF’s Skin Shader for Poser 12, 13 & 14… “This package contains the original ODF Skin Shader together with an Enhanced version by hborre, both provided as easy to use standalone material presets for Poser.”

MMX VDB Smoke FX 03, for steaming cauldrons and similar.

Scripts and helpers:

DC Texture Transformer 2, M4 Bundle. Convert M4 body textures to fit Genesis (all) and L’Homme.

BJ Pose Zone Plugin. Easily… “combine full-body and partial poses for all Genesis figures.”

BioFrom – Procedural Biological Materials as a plugin material-maker for Blender. Presumably the materials you make could also be imported into Poser, since it’s the same Cycles engine?

Currently free at DAZ, RunTimeDNA’s Render Studio Modular 1-4 + Scenes for Poser.

SculptTool For DAZ.

ND Cloth Simulation Toolkit for DAZ.

Tutorials:

Poser Meshlight Weirdness and how to fix it.

Want to make a ‘wobbly hand-held camera’ YouTube video watchable, by converting it to a slide-show of extracted stills? There’s a simple tutorial here that uses freeware.

Resources:

Sadly the Hivewive 3D forums were closed on 31st July 2026. On the Renderosity forums, there are currently two continuity threads, “Life after the Hive” and “Hivewire 3D forums… continued!”. Also, note the backup on Archive.org as Hive Wire Forums Backup June 2026.7z (250mb, expanding to 2Gb).

Software:

* Poser is now at Poser 14.0.439 (30th July 2026). I’ve picked out the most notable changes from the changelog.

* Windows Movie Maker 6.0 Setup for Windows 10 and 11. Yes, the classic Movie Maker, now working again on modern Windows!

* The free G’MIC 4.0.x has been released. Includes the usual .8BF Photoshop plugin, which also works with other graphics software that supports the .8BF plugin format. As usual, turn on the internal Internet switch and update after install, to get your custom presets back if they were based on experimental filters. Your custom G’MIC presets are stored in the Windows Registry.

* CorelDraw 2025, currently in a Humble Bundle for charity.

Generative software:

All free, as is the way of local AI tools.

* Aozora Trainer, a free local model trainer for SDXL-derived models, and the software is designed to run on a entry-level 3060 12Gb graphics card.

* Another ComfyUI <-> Photoshop bridge. Looks rather complex, but may appeal to some, and it apparently round-trips.

* Marlin-2B (GGUF) automatically indexes video thus…

Marlin-2B should be supported by the latest freeware Jan.ai local LLM/GGUF runner, as this now supports video input at last. However, note that back-end config is needed. Jan’s underlying llama.cpp requires both ffmpeg and ffprobe installed and on your system PATH in Windows… “without them, video requests will fail”. Theoretically Marlin/Jan.ai can then describe entire videos, but memory limitations mean that clips fed to Marlin 2B are best kept short on local desktop PCs.

* ComfyUI’s competitor InvokeAI has had an important security update. Also, among other important items it adds…

– Video generation support via Wan 2.2.
– Anima controlnets and inpainting.
– Multi-GPU support.

* Voicebox 0.5, a major release for this standalone portable Windows software. The slick GUI-based… “Voicebox stops being just a voice-cloning studio and becomes a full AI voice studio.”

That’s it for the mid/end July 2026 survey. More picks next month!

Release: Poser 14.0.439 (30th July 2026)

Posted on by Posted in Poser, Spotted in the News 1 Comment

Poser is now at Poser 14.0.439 (30th July 2026). Updates I noted since the Poser 14.0.227 release include, among many other items in the Changelog…

– Upgraded OpenGL from 2.2 to 4.3.
– Support for 8 lights in scene vs. 5 previously.
– GLSL now previews PrincipledBSDF, DiffuseBSDF, TransparentBSDF, Math nodes, Image Texture with alpha channel.

– HDRI environment maps correctly light and render as a background sphere. Rotation correctly dials 0-360 degrees.

– Area Light shape types in the property pane now contain Rectangle and Square.
– Increased the Shadow Blur Radius for the Infinite light.
– Shadow Blur Radius correctly works in Cycles [SuperFly].
– Eliminated pixelated shadows.
– Shadows from transparent objects no longer broken in FireFly renders.

– Fixed ability to apply animated Poses back to Props.
– Added the ability to save poses for props.
– Props can now save animations.

– Various Physics/Cloth fixes.
– User can now paint Rigidity onto cloth.
– Added Cloth Type presets Silk, Rubber, Cotton, Wool/Fleece, Denim, and Leather.

– Various Bullet Physics / collision fixes.
– Added per frame smoothing option to physics simulation settings and function.

– Focal distance indicator no longer malfunctions when animation keys are added.

– Online reference manual: New Help Topic for Gobo Lights.
– Gobo spotlight implemented for Cycles [SuperFly].
– Poser 14 correctly links to the Poser 14 reference manual.

So, a nice balance between updates for animators, and those who want better lighting and shadows. A major push forwards, by the look of it. Having “8 lights in scene” is reason enough on its own to upgrade.