2.2-14B-Rapid-AllInOne

I do not maintain this anymore. I've moved on to LTX2 which I find faster, more versatile and with far better quality than this ever had. Head over to https://huggingface.co/Phr00t/LTX2-Rapid-Merges for that.

These are mixtures of WAN 2.2 and other WAN-like models and accelerators (with CLIP and VAE also included) to provide a fast, "all in one" solution for making videos as easily and quickly as possible. FP8 precision. Generally the latest version available for each type of model (image to video or text to video) is recommended.

MEGA Merge: This is the "one model to rule them all" version which pretty much does everything. It can handle text to video, image to video, and first frame to last frame and last frame only (because it includes VACE). There is a specific workflow to use these merges included in the mega-v3/ folder, as it is slightly more complicated (but shouldn't be slower) due to its flexibility. See below for a screenshot of "mega" being used.

NSFW Merges: Degenerates should steer clear of these merges, as they are only for the most civilized people of culture or scientific researchers. These merge various spicy WAN 2.1+2.2 LORAs at generally low strengths to provide a "jack of all trades, master of none" all in one despicable solution. If you are not getting the results you want, add more LORAs or just use the non-NSFW versions with hand-picked LORAs.

You just need to use the basic ComfyUI "Load Checkpoint" node with these, as you can take the VAE, CLIP and Model all from one AIO safetensors (saved in your 'checkpoints' folder). All models are intended to use 1 CFG and 4 steps. See sampler recommendations for each version below.

WAN 2.1 LORA compatibility is generally still good, along with "low noise" WAN 2.2 LORA compatibility (do not use "high noise" LORAs). You might need to adjust LORA strengths (up or down) to get results you want, though.

MEGA version workflow screenshot (you can use VideoCombine instead of Preview Image):

MEGA I2V: Just bypass the "end frame" so the "start frame" will be your I2V starting frame. Keep everything else the same.

MEGA T2V: Bypass "end frame", "start frame" and the "VACEFirstToLastFrame" node. Set strength to 0 for WanVaceToVideo.

MEGA Last Frame: Just bypass the "start frame" and keep "end frame". Keep everything else the same as in the picture.

MEGA First->Last Frame: Use it like shown in the picture above.

Older non-MEGA workflows (v10 and below):

Seems to work even on 8GB VRAM:

CHANGELOG/VERSIONS:

base: This is the first attempt and very "stable", but mostly WAN 2.1 with few WAN 2.2 features. sa_solver recommended.

V2: This is a more dynamic mixture with more WAN 2.2 features. sa_solver OR euler_a sampler recommended. Suffers from minor color shifts and noise in I2V, typically just at the start.

V3: This is a mixture of SkyReels and WAN 2.2, which should improve prompt adherence and quality. euler_a sampler recommended, beta scheduler. Suffers from minor color shifts and noise in I2V, typically just at the start.

V4: WAN 2.2 Lightning in the mix! euler_a/beta recommended. I2V noise and color shifting generally improved, but motion is a bit overexaggerated.

V5: Improved overexaggeration of I2V model. euler_a/beta recommended.

V6: New merging structure and overall significantly improved quality. I2V noise for the first 1-2 frames still exists, but it clears up much better than previous versions. Some WAN 2.1 LORAs at heavy strengths may cause up to 5 poor early frames with T2V, where discarding (or lowering strengths) may help. sa_solver/beta recommended. I2V rarely suffers from some dramatic scene shifts.

V7: I2V scene shifting should be fixed, but some I2V noise persists (generally for just the first 1-2 frames). No changes needed for the T2V model, so that remains at V6. sa_solver/beta recommended.

V8: T2V is now based entirely off of WAN 2.2 "low" (with PUSA, SkyReels and Lightning accelerators mixed in), which should resolve noise problems with it (8.1 adds more SkyReels). I2V scaled back some of the WAN 2.2 mix, which was contributing to noise problems. There still is some minor I2V noise, but more of a delicate balance of WAN 2.2 + SkyReels to keep decent motion and flexibility. Euler_a/beta recommended.

V9: Removed PUSA and SkyReels from the WAN 2.2-side of I2V (and completely from T2V). as I think PUSA/SkyReels wasn't consistently helping (and sometimes hurting) when applied to WAN 2.2. This should provide a more reliable base to work from. euler_a/beta recommended, but feel free to experiment with sa_solver/beta or others!

V10: Fixes wrong accelerators being used (now WAN 2.2 Lightning in I2V and an an adaptive rank Lightx2v along with WAN 2.2 lightning in T2V). I2V now has a tendency to zoom into whatever is going on in your prompt, which I believe comes from increased camera movement from Wan 2.2 Lightning and being less tied to your initial image as the video progresses (so, prompt accordingly). Euler_a/beta still seems good.

MEGA v1: This is likely how I will continue making models, as I don't need separate I2V and T2V versions. No noise problems with I2V anymore! MEGA v1 is based off of WAN 2.2 "low T2V", then adds VACE Fun, SkyReels, FunReward and the usual accelerator/CLIP/VAE mix. Use the included workflow. ipndm/sgm_uniform sampler/scheduler recommended.

MEGA v2: Removed the FunReward LORA, which was causing faces to shift. I did notice some minor face shifting in the NSFW merge remaining, which I think is due to the LORA mixture, but it has been improved. Also reduced some of the SkyReels LORA a bit. ipndm/beta recommended.

MEGA v3: Very different merging method using SkyReels 2.1 33% base and WAN 2.2 66% on top. I now also match accelerators for each version (2.1 and 2.2), then merge. I think this gets a better result by basing "mega" on models designed for 1 sampler (2.1) but then bringing in most of WAN 2.2 to lay on top. Camera control and prompt following is better, but keeping facial features still struggles compared to v10 I2V (might be a VACE limitation). ipndm/beta recommended. euler_a/beta seems to work better with the NSFW v3.1 merge, though.

MEGA v4: Uses the WAN 2.2 finetune from https://huggingface.co/eddy1111111/WAN22.XX_Palingenesis (also slight tweaks to accelerator strengths)

MEGA v5: New merging method with very experimental accelerator mix! I include small amounts of many I2V and T2V accelerators on top of WAN22.XX_Palingenesis and SkyReels 720p, plus VACE. The goal is to improve I2V consistency without hurting T2V. I think quality, detail and consistency has improved, but I do wish camera control was better. euler_a/beta recommended.

MEGA v6: Adjusted accelerators, bringing in more of the older Lightx2v as relying too much on the newest WAN 2.2 Lightning was hurting motion. I'm seeing better camera movement and prompt adherence in my testing than v5. NSFW v6.1 version has newer LORAs included and tweaked parameters. sa_solver/beta recommended.

MEGA v7: Now uses 3 different accelerators mixed together: lightx2v, WAN 2.2 Lightning (250928) and rCM. Motion seems to be improved further. euler_a/beta seems to work pretty good.

MEGA v8: Updated rCM 720p accelerator, which is now the biggest accelerator in the mix, reducing lightx2v and WAN 2.2 Lightning. Updated NSFW LORAs a bit. euler_a/beta still recommended.

MEGA v9: Removed SkyReels 2.1 720p completely. This is now based completely on WAN22.XX_Palingenesis T2V + VACE, using mostly rCM 720p for acceleration. Updated MysticXXX v2 for the NSFW merge among other tweaks. Motion should be better, hopefully. euler_a/beta recommended.

MEGA v10: Packed the models a bit differently, tweaked acclerators and NSFW LORAs some more. I tried to test this version a bit more and was getting better results. euler_a/beta recommended.

MEGA v11: Mostly the same as v10, but pulled in the latest WAN 2.1 distill from lightx2v. euler_a/beta recommended.

MEGA v12: Big update! Using bf16 Fun VACE WAN 2.2 as a base now, getting rid of "fp8 scaled" issues. Significantly tweaked NSFW LORAs, even putting a dash of "high noise" Dreamlay into the mix. Only uses rCM and Lightx2V accelerators now for better motion. v12.1 improves cumshots. dpmpp_sde/beta recommended.

Looking for GGUFs? Check the sidebar for quants.

Looking for FP16 precision? TekeshiX has been helping me build variants in FP16 format (but they are kinda outdated):

https://huggingface.co/TekeshiX/RAPID-AIO-FP16/tree/main

DISCLAIMER: As you may expect, some compromises had to be made to reach this level of speed and simplicity. If you want more complex workflows and longer generation times to run "full WAN 2.2"'s pair of models (which will give higher quality results), or control over accelerator LORAs included in this merge, there are many resources elsewhere to do that.