# V1-H — final results

30 planned videos completed; 0 auxiliary outputs; 0 planned LTX-2.5 slots skipped because access is gated. All actual outputs have verified metadata, full decode checks and explicit visual scores.

All hero outputs are fresh renders using the ten selected V1 prompts. The four mandatory F1/F2 anime/real prompts are included; the other six were selected by grid scores. Wan uses seeds 24601/24602 and Hunyuan uses 24603. This is the plan's unequal 2:1 allocation, not matched-noise repeats or enough samples for a population-level ranking. Prompts and fixed seeds were retained when quality failed; no quality-driven rerolls were used. Wan 20-step SageAttention2 was adopted only after its separate smoke control and first 720p hero review. Hunyuan remained the second model after the matched Kandinsky candidate failed the precommitted replacement threshold; see V0A for that control.

For the action prompts, Wan generally gives more active sword exchanges, while Hunyuan often gives a short parry followed by held stances. Useful sword examples are Wan F1_real seed 24601 and Wan S2_F1 seed 24602; Wan F1_anime seed 24601 is a useful anime example. Blade alignment, grip precision and support mechanics remain imperfect even in these stronger clips. Hunyuan preserves anime styling in F2_anime, whereas both Wan F2_anime samples become photographic. Wan F2_anime seed 24602 also changes the red-gloved fighter's hair/face after a fall, a major identity failure. None of the six F2 hero outputs completes a clear controlled throw on dense 60-sample review; kicks, blocks, falls or final clinches do not substitute for that requested action.

Dance varies strongly by seed and model. Wan M2 seed 24601 and Hunyuan M2 seed 24603 show readable ordinary hip-hop stepping with full bodies; Wan M2 seed 24602 instead produces sustained acrobatic breakdancing with less convincing inverted support. Wan S2_M2 seed 24602 is the strongest social-partner-dance example, with a turn, coordinated motion and stable full-body framing. Wan S2_M2 seed 24601 resembles contemporary dance with imperfect synchronization. Hunyuan S2_M2 seed 24603 adds a third adult and mostly shows modest steps/clapping, missing the requested two-person synchronized dance.

Framing is a recurring limitation. Both Wan Mara street-walk seeds and the Hunyuan version tighten enough to crop the lower body; one Wan seed also omits the turn. Hunyuan's simpler M1 walk crops the legs throughout, preventing gait assessment. Wan M1 seed 24601 maintains full-body walkaway framing, but its hidden face cannot substantiate facial integrity. Wan M1 seed 24602 crops the feet late. The T2V character description is not a reference-image identity test; exact freckle and hair-color adherence is incomplete.

The two Wan 4:3 bridge seeds only partly match the requested saturated-primary, soft-focus 1970s television look. Seed 24601 is clean and modern with a weak walk-stop-turn and tighter framing; 24602 better follows the staging and keeps the body visible but is very dark. Hunyuan instead produces cel-shaded animation: the officer walks straight toward camera without a clear stop-and-turn, while the frame pushes into a large close-up. Its colorful bridge does not rescue the requested film/television style and staging.

Review scores are subjective on the five PLAN axes. All clips were inspected across nine evenly spaced frames; F2action clips and selected uncertain action clips also received 60 samples at 12 fps. Hidden, distant or backlit faces, small background lettering and ambiguous contact are explicitly disclosed per clip. No silent clip is assigned a lip-sync score. Scores and visual artifacts are distinct from technical render success.

Final encoding changed during recovery of Wan M2 seed 24601: earlier clips were re-encoded as H264/yuv420p with FFmpeg libx264 CRF18; subsequent already compliant native streams are preserved using faststart remux with metadata stripped. A redundant full-resolution encoder stall was recovered from the existing successful ComfyUI history without repeating inference. Every final still passes metadata and full-decode checks. Compression-level pixel differences across this boundary should not be attributed to model quality. Execution time includes loading and decoding; VRAM is sampled total GPU0 residency, not isolated model allocation.

Timing includes ComfyUI execution and may include cold loading. Sampled peak GiB is total GPU0 residency, not isolated model allocation. Visual scores use the five PLAN axes; additional reference or likeness assessments are separate. No phoneme-level lip-sync accuracy is inferred from silent clips.

| Test | Role | Settings | Seconds | Peak GiB | Scores | Review / flags |
|---|---|---|---:|---:|---|---|
| V1-H_F1_anime_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 923.47 | 66.76 | {"adherence": 4, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Two distinct adult anime swordsmen raise weapons, make short blade contacts/parries and step apart in a plain courtyard. Full bodies remain visible, with coherent cel-shaded styling, clothing and background. Motion is restrained and pose-held, with limited footwork and weak sense of impact; blade curvature/length and small hand alignment vary. Identity stays readable and no conspicuous doubled face is apparent. This delivers anime style, but the action is less vigorous than the stronger Wan sword samples. Flags: {"artifacts": "held poses and limited footwork; variable blade/hand geometry", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_F1_anime_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 545.36 | 90.93 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced frames and full-resolution2s. Two distinct anime adult fighters in green and orange remain in full-body framing through lunges, raised guards and repeated sword crossings/parries. Coherent single faces and stable courtyard; anime rendering is maintained. Blade length/curvature changes and hand-to-hilt contact becomes ambiguous during a raised guard; foot contacts slide somewhat. No doubled face or catastrophic instability. First720p Sage2 hero passes workflow review; retained imperfections are model-quality findings. Flags: {"artifacts": "changing sword geometry, ambiguous grip and some sliding foot contact", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F1_anime_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 488.08 | 72.27 | {"adherence": 4, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced frames. Two anime fighters remain distinct in a full-body courtyard shot and perform a short sword exchange with lunges/parries before separating into a prolonged pause. A small hop and some sliding support weaken physical realism; blade shape and grip alignment vary. Clothing, main faces and architecture remain coherent at sampled times, with no apparent doubled foreground face. Anime style holds, but action is less sustained than seed24601. Flags: {"artifacts": "variable sword geometry/grips; floaty hop and sliding foot contacts", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F1_real_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 828.03 | 66.39 | {"adherence": 4, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Two realistic adult swordsmen raise and cross their weapons during a brief controlled exchange, shift position and settle into facing poses in a courtyard. Full bodies, identities, dark uniforms and setting stay coherent. Much of the latter clip is held stance, with limited dynamic footwork; blade/hand alignment and wrist geometry fluctuate during the raised parry. Separation is modest. No conspicuous duplicated main face at sample scale, but profiles and distance limit fine facial assessment. Flags: {"artifacts": "brief action followed by long holds; variable wrist/blade geometry", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_F1_real_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 488.25 | 71.76 | {"adherence": 5, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced frames. Two distinct realistic adults exchange controlled sword strikes and raised parries, lunge, reset and separate in a plain stone courtyard. Both bodies and feet remain visible. Clothing and faces stay coherent at sampled times, with readable contact and more sustained action than the earlier paused anime seed. Some blade edges/lengths and hand-to-hilt alignment vary; stance transitions are slightly stiff. No visible doubled face, overlay text or watermark. Flags: {"artifacts": "minor sword geometry/grip variation and stiff footwork", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F1_real_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 495.35 | 72.27 | {"adherence": 4, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced frames. Two realistic adults in teal and black exchange sword gestures/parries and move around a plain courtyard, remaining in full-body view. Identity, clothing and stonework are coherent. Right fighter makes an unmotivated hopping/skipping motion, and the exchange gives way to approaching/resetting rather than consistently controlled combat. Blade length/alignment and foot support vary. The back-facing left fighter limits facial assessment; no apparent doubled main face in visible views. Flags: {"artifacts": "hopping/sliding footwork and changing sword alignment", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F2_anime_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 829.22 | 53.42 | {"adherence": 3, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine whole-clip samples and60samples at12fps. Two distinct anime martial artists perform kicks, guards and punches on a mat; the final action is close grappling rather than a completed controlled throw. Anime styling is retained, unlike both Wan F2anime seeds. Feet/lower legs are cropped for much of the clip, failing the full-body-wide requirement and limiting support assessment. Held poses, sliding turns and unclear hand/limb contacts in the final clinch reduce motion realism. Clothing, identities and background are otherwise stable, with no conspicuous doubled main face at sample scale. Flags: {"artifacts": "lower-leg crop; no completed throw; ambiguous final clinch contacts", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_F2_anime_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 488.27 | 72.30 | {"adherence": 3, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 1} | Reviewed nine whole-clip frames plus60samples at12fps over the first5s. Two distinct adult martial artists perform kicks, blocks/leg catches and resets in a training gym, staying in full-body view. No controlled throw occurs in the dense sequence. The output is photographic/live-action rather than the requested anime, a clear style failure. Identities and bodies stay coherent; extended kick holds, minor sliding/hopping and hand/foot contact ambiguities remain. This valid render is retained without reroll. Flags: {"artifacts": "style failure; minor contact and support inaccuracies", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F2_anime_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 490.81 | 71.76 | {"adherence": 3, "motion": 3, "anatomy_face": 3, "temporal": 2, "style": 1} | Reviewed nine whole-clip samples,60samples at12fps and full-resolution first/4.3s frames. Photographic sparring again misses requested anime style. Two fighters kick and block; the red-gloved fighter falls near the other feet, but a controlled throw mechanism is not clearly readable. Crucially, the red-gloved fighter changes from a long ponytail and clean face to short hair and a beard after the fall, a major identity-continuity failure. Contact/occluded-limb geometry is ambiguous. Gym wall lettering is malformed. Retained quality failure without reroll. Flags: {"artifacts": "major identity change after fall; style failure and ambiguous contact mechanics", "text_garbling": true, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F2_real_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 842.17 | 52.54 | {"adherence": 3, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine whole-clip samples and60samples at12fps. Two realistic adult martial artists kick, guard/block and exchange hand contacts on a training mat. The ending resembles a leg catch/clinch; no completed controlled throw occurs. Lower legs/feet are cropped in several views, so sustained full-body framing is missed. Identities, dark outfits and background remain coherent. Extended held kicks, sliding resets, unclear wrist contacts and the final intertwined limbs weaken physical realism. No conspicuous doubled main face at review scale; contact anatomy remains partly ambiguous. Flags: {"artifacts": "no completed throw; intermittent lower-body crop and unclear clinch/contact mechanics", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_F2_real_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 488.09 | 64.89 | {"adherence": 3, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine whole-clip samples and60samples at12fps. Two realistic adult martial artists kick, block and reset on a mat, staying in full-body view with stable clothing and identities. No controlled throw occurs. Several extended leg holds, hopping resets and ambiguous hand-to-foot contact reduce physical realism, but the exchange is readable and no conspicuous duplicate face or extra limbs are apparent at sample scale. Retained without reroll. Flags: {"artifacts": "minor contact/support inaccuracies; requested throw absent", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_F2_real_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 488.14 | 64.89 | {"adherence": 3, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine whole-clip samples and60samples at12fps. Two adult martial artists in white uniforms exchange high kicks, punches and blocks in a realistic training gym. Full bodies remain visible and the distinct identities, uniforms and setting are coherent. No controlled throw occurs. Some extended kick holds, hopping/sliding resets and uncertain limb contact remain; no conspicuous doubled main face at review scale. Background spectators are small and soft. Retained without reroll. Flags: {"artifacts": "minor foot support/contact inaccuracies; requested throw absent", "text_garbling": false, "watermark": false} Final encoding: FFmpeg libx264 CRF18 yuv420p faststart (legacy collector) |
| V1-H_M1_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 831.88 | 39.79 | {"adherence": 3, "motion": 3, "anatomy_face": 4, "temporal": 5, "style": 5} | Reviewed nine evenly spaced whole-clip frames. An adult woman walks away along a city sidewalk in a stable rear tracking view. Hair, tan jacket, dark trousers and street architecture remain coherent. Framing stays around head-to-hip/thigh throughout, cropping legs and feet and failing the explicit full-body requirement. Small arm/shoulder movements suggest walking, but gait, foot support and facial integrity cannot be assessed from this view. No conspicuous duplication in the visible upper body; background signage is too small to evaluate. Flags: {"artifacts": "persistent lower-body crop; gait and face hidden", "text_garbling": "background signs too small to assess", "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_M1_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 490.18 | 64.77 | {"adherence": 5, "motion": 4, "anatomy_face": 4, "temporal": 5, "style": 5} | Reviewed nine evenly spaced whole-clip frames. A single main adult woman walks away down a city street in sustained full-body tracking/wide framing. Her silhouette, blonde hair, black jacket and pale skirt remain coherent, as do the paving, lamp posts and buildings. Gait and foot placement are plausible at the small subject scale, with slight sliding uncertainty. The main face is not visible, so facial integrity is unassessed rather than proven. Background people and storefront lettering are small; no conspicuous overlay watermark or main-body duplication is apparent. Flags: {"artifacts": "minor distant-foot ambiguity; face hidden throughout", "text_garbling": "background lettering too small to assess", "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_M1_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 489.08 | 64.77 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 5, "style": 5} | Reviewed nine evenly spaced whole-clip frames. An adult woman in a brown jacket and dark skirt walks toward camera along a busy city street, carrying a shoulder bag and glancing aside. Main identity, clothes, bag and city geometry remain coherent, with plausible alternating steps and arm motion. Camera framing grows progressively tighter; feet are cut off near the end, so the full-body requirement is only partly met. Small/distant background pedestrians limit fine anatomy assessment. No conspicuous doubled main face; storefront text is too small to evaluate reliably. Flags: {"artifacts": "late foot crop; minor distant anatomy uncertainty", "text_garbling": "background lettering too small to assess", "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_M2_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 829.60 | 40.31 | {"adherence": 5, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. A single adult dancer performs hopping steps, knee bends, hip shifts and side lunges on a spacious studio floor. Full-body wide framing is maintained, with stable black shirt, beige trousers, face and curtain/mirror background. Choreography reads as ordinary hip-hop stepping rather than the acrobatic interpretation of Wan seed24602. Some foot sliding/weight-transfer ambiguity and small-hand softness remain. No conspicuous doubled face or added limbs at review scale. Flags: {"artifacts": "minor foot-support and hand-detail ambiguity", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_M2_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 488.99 | 64.89 | {"adherence": 5, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. A single adult dancer performs varied crossing steps, arm swings, bends and low transitions on a spacious studio floor, in full-body wide framing. Identity, white overshirt, dark trousers and studio geometry remain coherent. Movement reads as hip-hop footwork; minor foot sliding/support ambiguities and small soft hands remain. No conspicuous duplicate face or extra limb at this review scale. Native H264 output was recovered by faststart remux after redundant re-encoding stalled; inference was not repeated. Flags: {"artifacts": "minor foot support and small-hand softness", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_M2_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 488.50 | 64.89 | {"adherence": 4, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine whole-clip frames and60samples at12fps. The hip-hop-step prompt becomes sustained acrobatic breakdancing: one-hand support, leg sweeps, inversion and head/shoulder-supported rotations. Full body and spacious sunlit studio are retained. Clothing and background remain stable, but repeated inverted spins, hand/head support transitions and leg geometry are approximate rather than convincingly weight-bearing. Face is frequently hidden or tiny, limiting facial assessment. No conspicuous added limbs at sample scale. The first seed is the clearer example of ordinary stepping choreography. Flags: {"artifacts": "approximate inverted support/contact and leg mechanics", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_F1_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 829.14 | 40.31 | {"adherence": 4, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Two realistic adult swordsmen make a brief raised strike/parry, lower their blades and separate in a naturally lit courtyard. Full bodies and the broad sequence remain readable, with coherent identities, shirts and architecture. Footwork is limited and much of the later clip is a held stance. Blade alignment/length, grip and wrist geometry vary around the contact. No conspicuous duplicated main face at review scale; the result is less dynamic than the stronger Wan sword samples. Flags: {"artifacts": "limited footwork/long holds; variable blade and wrist alignment", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_F1_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 492.30 | 64.77 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine whole-clip frames and60samples at12fps. Two realistic adults perform visible sword contacts/parries, lunges and an added side kick in a sunlit courtyard, then separate/reset. Full bodies remain in view; identities, costumes and courtyard geometry are coherent. The exchange is active and readable, but grip/blade alignment varies during fast movement and the low crouch-to-kick transition has uncertain support mechanics. Blades are briefly hard to distinguish against the background; no sustained third weapon or duplicated main face is established at review scale. Flags: {"artifacts": "variable blade/grip geometry; approximate low-kick support", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_F1_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 489.40 | 64.66 | {"adherence": 5, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Two realistic adult swordsmen exchange visible strikes/parries in a courtyard, then lower their weapons and separate. Full-body wide framing and readable stepping are maintained, with stable outfits, identities and architecture. Minor blade-length/alignment, grip and foot-support inconsistencies remain, but the requested action sequence is clear. Faces are relatively small and one is frequently in profile/back view. The wall plaque is too small to evaluate its lettering reliably; no overlay watermark or conspicuous doubled main face. Flags: {"artifacts": "minor blade/grip and support inconsistencies", "text_garbling": "background plaque too small to assess", "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_M1_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 830.44 | 39.76 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. A woman with a short wavy dark bob, teal jacket, charcoal trousers and brown boots walks away along a sunlit street, then turns toward camera. Photographic face, clothing and environment remain coherent. The camera rapidly pushes from full-body tracking to chest/head close-up, failing sustained full-body framing and limiting later gait assessment. The specific cheek freckle is not established and auburn hair color is weak. Visible walking and turn are plausible; no conspicuous doubled face. Flags: {"artifacts": "strong push-in crops lower body; fine character details incomplete", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_M1_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 489.86 | 64.89 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. A woman with short auburn bob, teal jacket, dark trousers and brown boots walks away along a sunlit street, then turns toward camera. Natural-light photographic styling and visible identity are coherent. The tracking camera progressively pushes from full-body to waist/chest/head framing, violating sustained full-body framing and limiting late gait assessment. Small freckle and eye-color details cannot be confirmed at this scale. Initial walking/support is plausible with minor foot-placement uncertainty; no apparent doubled face. Flags: {"artifacts": "progressive camera push-in crops lower body", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_M1_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 492.29 | 64.77 | {"adherence": 3, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Short auburn hair, teal belted jacket, dark trousers and brown boots match the broad description, with a stable photographic face and sunlit street. The woman is already facing camera and walks forward throughout, so no requested turn is established. Framing progressively crops feet and then lower legs, missing sustained full-body tracking. Walking and arm swing appear plausible where visible; background pedestrians are small and soft. Freckle/eye-color details are unconfirmed at this scale; no conspicuous doubled main face. Flags: {"artifacts": "lower-body crop; requested turn absent", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_M2_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,1280x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 851.53 | 40.31 | {"adherence": 2, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. The scene contains three clearly separate adults rather than the requested two. A pair on the left makes small steps/turns while the man on the right mainly claps/gestures, reading like a loose dance lesson rather than synchronized social partner dancing. Full-body wide framing and natural-light photographic styling are retained. Individual identities, outfits and studio background remain coherent. Motion is modest with hand/contact ambiguity, but no conspicuous duplicated main face; the extra person is a distinct additional subject, not a reflection. Flags: {"artifacts": "extra third adult; weak synchronized-dance action; hand/contact ambiguity", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_M2_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 488.69 | 64.77 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Two realistic adult dancers remain fully visible in a spacious bright studio, performing broadly coordinated arm extensions, raised knees, side kicks and lunges. Their faces, clothing and the room remain recognizable. Choreography reads more as contemporary/rehearsal dance than a social partner dance, and the two poses are not consistently synchronized. Minor foot-support and hand-shape ambiguities remain. Background mirror/reflection figures are present, so they are not counted as additional foreground dancers; reflection accuracy is not established. No conspicuous doubled foreground face. Flags: {"artifacts": "minor hand/support geometry; imperfect synchronization", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S2_M2_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,1280x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 489.65 | 64.77 | {"adherence": 5, "motion": 4, "anatomy_face": 4, "temporal": 5, "style": 5} | Reviewed nine evenly spaced whole-clip frames. Two adult partners perform coordinated side steps, hand-held approaches/separations and an underarm turn in a spacious naturally lit studio. Full bodies remain visible, with stable clothing, silhouettes, room geometry and lighting. This seed reads clearly as social partner dance, unlike the contemporary choreography of seed24601. Minor hand-contact/support ambiguities remain. Faces are small and backlit, so fine facial anatomy cannot be fully assessed; no conspicuous doubled foreground face is apparent. Flags: {"artifacts": "minor hand-contact and foot-support ambiguity", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S5_M1_hunyuan15-t2v-fp16_24603 | primary | 20steps,cfg6,shift9,960x720,121frames,24fps; VAE tiles512 overlap64 temporal64 overlap8,seed24603 | 531.39 | 39.23 | {"adherence": 2, "motion": 3, "anatomy_face": 4, "temporal": 4, "style": 2} | Reviewed nine evenly spaced whole-clip frames. An animated officer in a blue uniform walks straight toward camera on a colorful bridge, with no clear stop-and-turn sequence. The correct4:3 frame progressively tightens from wide/full-body to a large face close-up. Cel-shaded animation, sharp outlines and vivid space imagery replace the requested soft-focus1970s film/television look. Face, uniform and bridge stay mostly coherent, but gait is simple and then hidden by cropping. No conspicuous doubled face; retained style/staging failure without reroll. Flags: {"artifacts": "animated-style substitution; no turn; strong push-in and lower-body crop", "text_garbling": "small console markings unassessed", "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S5_M1_wan22-t2v14-full-sage2-fp8_24601 | primary | 20steps,cfg3.5,960x720,81frames,16fps,seed24601; SageAttention2 auto per-model override | 314.04 | 57.83 | {"adherence": 3, "motion": 4, "anatomy_face": 4, "temporal": 4, "style": 3} | Reviewed nine evenly spaced whole-clip frames. A coherent adult female officer in a teal uniform moves across/around a bridge console with a stylized star-and-planet backdrop. She looks aside and leans toward the foreground; a deliberate walk-stop-turn-to-camera sequence is weak. The 4:3 frame is correct, but the subject becomes medium/close and the console obscures her lower body. Clean modern lighting, muted uniform and crisp detail only partly evoke the requested soft-focus1970s saturated-primary television look. Face and outfit remain stable, with some hand uncertainty near the console; no conspicuous doubled face. Flags: {"artifacts": "partial style mismatch; foreground console occlusion and tighter framing", "text_garbling": false, "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |
| V1-H_S5_M1_wan22-t2v14-full-sage2-fp8_24602 | primary | 20steps,cfg3.5,960x720,81frames,16fps,seed24602; SageAttention2 auto per-model override | 313.05 | 58.22 | {"adherence": 4, "motion": 4, "anatomy_face": 4, "temporal": 5, "style": 3} | Reviewed nine evenly spaced whole-clip frames. An adult female officer walks laterally across a starship bridge, stops, turns toward camera and resumes a small forward step. Correct4:3 wide framing retains the full body much better than seed24601. Character silhouette, uniform and bridge geometry remain stable. The scene is very dim, with muted olive clothing and modern-looking console lighting rather than saturated-primary soft-focus1970s television. Darkness limits fine face/hand assessment; gait is plausible at sample scale and no conspicuous body duplication is apparent. Flags: {"artifacts": "very dark subject; partial retro-style mismatch", "text_garbling": "small console markings unassessed", "watermark": false} Final encoding: Native H.264/yuv420p preserved; FFmpeg faststart remux, metadata stripped |

Viewing aids: [mandatory fight comparison](comparisons/fights_three_seeds.mp4), [comparison description](comparisons/README.md), [descriptive scores/runtime chart](hero_descriptive_comparison.png), [chart SVG](hero_descriptive_comparison.svg), and [comparison CSV](hero_descriptive_comparison.csv). The chart legend and the montage layout were visually inspected; comparison video metadata and full decode passed. These are derived public viewing aids, not additional model renders.